Computer-readable data from the 1980 census Include both summary data and microdata. Summary data include Summary Tape Files (STF's) 1 to 5, which are generally comparable to the First Count through Sixth Count files from the 1970 census. In addition to the files in the STF series, other summary data released by the Bureau include a P.L. 94171 Population Counts file for use in reapportionment/redistricting (released in February/March, 1981) and the Master Area Reference File which provides geographic items from STF 1 and selected population and housing items (all individual State files released beginning September 1981). All of these files contain data summarized to various levels of geography. Microdata files, on the other hand, contain disclosure- free household and person records from the census. These files are similar to the 1970 Public Use Sample files and will be available in mid to late 1982.

Summary Tape Files vary by summary level of geography, detail of information, and whether they include 100-percent or sample data. STF's 1 and 2 provide data based on the set of census questions asked of all persons and housing units. These data are 100-percent data. STF's 3, 4, and 5 are based on sample data. These data are estimates based on the responses of a sample of the population and housing units and contain more extensive housing and population information. In 1980, the sampling rate was 1 in 2 in governmental units estimated to have less than 2,500 inhabitants and 1 in 6 elsewhere. Overall the sampling rate was approximately 1 in 5. The Bureau's 1977 population estimates were used to determine the sampling rate for a given area.

The geographic detail of STF 1 is the maximum possible detail available from the census: data for individual blocks in block- numbered areas and for enumeration districts outside block-numbered areas. The lowest level of geography provided by STF 2 is census tract, or minor civil division/census county division (MCD/CCD) and places of 1,000 or more inhabitants in nontracted areas. The lowest level for STF 3 is the block group or enumeration district, while the smallest geographic unit for STF 4 is census tract, or MCD/CCD and places of 2,500 or more inhabitants in nontracted areas. STF 5's lowest geographic level is the standard metropolitan statistical area (SMSA), central city(ies), other places of 50,000 or more inhabitants, and counties of 50,000 or more inhabitants.

STF's 1 to 4 each consist of multiple files labeled A, B, and C. Each file features specific levels of geography. Figure 8 details the geographic levels on each STF.







For comparison purposes, STF 1 is similar in subject matter and geographic detail to the First and Third Count files for 1970. STF's 2 and 4 are roughly comparable to the 1970 Second and Fourth Counts, respectively. STF 3 is comparable to the 1970 Fifth Count, while STF 5 corresponds to the 1970 Sixth Count. To summarize, STF 1 contains more detailed geography but less subject matter detail than STF 2.

Similarly, STF 3 contains more detailed geography but less subject matter detail than STF 4. STF's 1 and 2 contain complete count data, while STF's 3 and 4 contain sample estimates. Finally, STF 5 contains sample estimates aggregated to a higher level of geography than the other files, but which are presented in the most subject matter detail.

Users may need certain types of maps for the geographic area(s) they are extracting from the file(s). To determine which maps best define the geographic area(s), compare the geographic coverage of each file (see Appendix A) with the description of each type of 1980 census map (see below).

The maps used in conjunction with the above summary tape files consist of five basic types: county maps, place maps, place-and-vicinity maps, Indian Reservation maps, and Metropolitan lap Series (MMS) or Vicinity Map Series (VMS). Ordering information for these maps may be obtained from Data User Services Division, Customer Services (Maps), Bureau of the Census, Washington, D.C. 20233.

All five map types have several characteristics in common:

--To improve legibility, most 1980 maps are at a larger scale than were the comparable l970 maps.

--Symbols used for the various boundaries are consistent for all five types of maps.

--Names, identifying numbers, and boundaries are shown 'where appropriate on al1 maps for counties and equivalent entities, minor civil divisions (MCD's) or census county divisions (CCD's), places, American Indian reservations and Alaska Native villages, census tracts or block numbering areas (BNA's) where present, enumeration districts (ED'S)(in those areas which are not block numbered), and blocks.

--All maps show metric, feet, and mile scales.

--All maps containing block-numbered areas will be available from the U.S. Government Printing Office.

The following paragraphs present a brief description of each type of map.

The following is a list of reference materials which provide additional information concerning the 1980 census.

The data available on STF 3 are based on the 1980 census sample. The data are estimates of the actual figures that would have resulted from a complete count. Estimates can he expected to vary from the complete count result, because they are subject to two basic types of error---sampling and nonsampling. The sampling error in the data arises from the selection of persons and housing units to be included in the sample. The nonsampling error, which affects both sample and complete count data, is the result of all other errors that may occur during the collection and processing phases of the census. A more detailed discussion of both sampling and nonsampling error and a description of the estimation procedure are provided below.

While every person and housing unit in the United States was enumerated on a questionnaire that requested certain basic demographic information (e.g. age, race, relationship), a sample of persons and housing units was enumerated on a questionnaire that requested additional information. The basic sampling unit for the 1980 census was the housing unit, including all occupants. For persons living in group quarters, the sampling unit was the person. Two sampling rates were employed. In incorporated places of less than 2500 persons (based on precensus estimates), one-half of all housing units and persons in group quarters were to be included in the sample. In all other places, one-sixth of the housing units or persons in group quarters were sampled. The purpose of this scheme was to provide relatively more reliable estimates for small places. When both sampling rates were taken into account across the Nation, approximately 19 percent of the Nation's housing units were included in the census sample.

The sample designation method depended on the data collection procedures. In about ninety-five percent of the country, the census was taken by the mailout/mailback procedure. For these areas, the Bureau of the Census either purchased a commercial mailing list which was updated and corrected by Census Bureau field staff, or prepared a mailing list by canvassing and listing each address in the area prior to Census Day. These lists were computerized, and every sixth unit (for l-in-6 areas) or every second unit (for l-in-2 areas) was designated as a sample unit by computer. Both of these lists were also corrected by the Post Office.

In non-mailout/mailback areas, a blank listing book with designated sample lines (every sixth or every second line) was prepared for the enumerator. Beginning about Census Day, the enumerator systematically canvassed the area and listed all housing units in the listing book in the order in which they were encountered. Completed questionnaires, including sample information for any housing unit which was listed on a designated sample line, were collected.


In both types of data collection procedure areas, an enumerator was responsible for a small geographic area known as an enumeration district, or ED. An ED usually represented the average workload area for one enumerator.

In order to reduce the cost of processing, a scheme was designed while the sample questionnaires were being processes, to select a sample of questionnaires on which the place of work and migration data items would be coded. The sample questionnaires were processed by work units consisting of 1980 census EDs. In work units (EDs) where the place of work and migration data items had not yet been coded, every other sample questionnaire within the work unit was selected for these coding operations. In work units where the place of work and migration data items already had been coded, all sample questionnaires were included in the tabulation.

Since the data in this file are based on a sample, they may differ somewhat from complete-count figures that would have been obtained if all housing units, persons within those housing units, and persons living in group quarters had been enumerated using the same questionnaires, instructions, enumerators, etc. The deviation of a sample estimate from the average of all possible samples is called the sampling error. The standard error of a survey estimate is a measure of the variation among the estimates from the possible samples and thus is a measure of the precision with which an estimate from a particular sample approximates the average result of all possible samples. The sample estimate and its estimated standard error permit the construction of interval estimates with prescribed confidence that the interval includes the average result of all possible samples. The method of calculating standard errors and confidence intervals for the data on STF 3 is given below. In addition to the variability which arises from the sampling procedures, both sample data and complete-count data are subject to nonsampling error. Nonsampling error may be introduced during each of the many extensive and complex operations used to collect and process census data. For example, operations such as editing, reviewing, or handling questionnaires nay introduce error into the data. A more detailed discussion of the sources of nonsampling error is given in the section on Control of Nonsampling Errors.

Nonsampling error may affect the data in two ways. Errors that are introduced randomly will increase the variability of the data, and should therefore be reflected in the standard error. Errors that tend to be consistent in one direction will make both sample and complete-count data biased in that direction. For example, if respondents consistently tend to underreport their income, then the resulting counts of households or families by income category will be below the actual figures. Such biases are not reflected in the standard error.

1. Totals and Percentages. Tables A through C, pages 204-208, contain the information necessary to calculate the standard errors of sample estimates in this file. In order to perform this calculation, it is necessary to know the unadjusted standard error for the characteristic, given in table A or B, that would result under a simple random sample design (of persons, families, or housing units) and estimation technique; the adjustment factor for the particular characteristic estimated, illustrated in table
C; and the number of persons or housing units in the tabulation area and the percent of these units in sample, derivable from each STF 3 record. The adjustment factors reflect the effects of the actual sample design and complex ratio estimation procedure used for the 1980 census.

To calculate the approximate standard error of an estimate, follow the steps given below.

a.Obtain the unadjusted standard error from table A or B (or from the formula given below the table) for the estimated total or percentage, respectively;

b.For the geographic tabulation area with which you are working, compute the "percent in sample" by dividing the appropriate unweighted sample count by the corresponding 100-percent count. For person and family characteristics these figures are found in STF 3 tables 2 and 3; for household and housing unit characteristics these figures are found in STF 3 tables 5 and 6.

c. Use table C to obtain the factor for the characteristic (e.g. work disability, school enrollment) and the range that contains the percent in sample with which you are working. Multiply the unadjusted standard error by this factor. If the estimate is a cross tabulation of more than one characteristic, use the largest factor.

As is evident from the formulas below tables A and B, the unadjusted standard errors of zero estimates or of very small estimated totals or percentages approach zero. This is also the case for very large percentages or estimated totals that are close to the size of the tabulation areas to which they correspond. These estimated totals and percentages are, nevertheless, still subject to sampling and nonsampling variability, and an estimated standard error of zero (or very small standard error) is not appropriate.

For estimated percentages that are less than 2 or greater than 98, use the unadjusted standard errors in table B that appear in the 2 or 98 row. For an estimated total that is less than 50 or within 50 of the total size of the tabulation area, use an unadjusted standard error of 16.


As is evident from the formula below tables A and B, the unadjusted standard errors of zero estimates or of very small estimated totals or percentages approach zero. This is also the case for very large percentages or estimated totals that are close to the size of the tabulation areas to which they correspond. These estimated totals and percentages are, nevertheless, still subject to sampling and nonsampling variability, and an estimated standard error of zero (or very small standard error) is not appropriate.

For estimated percentages that are less than 2 or greater than 98, use the unadjusted standard errors in table B that appear in the 2 or 98 row. For an estimated total that is less than 50 or within 50 of the total size of the tabulation area, use an unadjusted standard error of 16.



This method, however, will underestimate (overestimate) the standard error if the two items in a sum are highly positively (negatively) correlated or if the two items in a difference are highly negatively (positively) correlated. This method may also be used for the difference between (or sum of) sample estimates from two censuses or between a census sample and another survey. The standard error for estimates not based on the 1980 census sample must be obtained from an appropriate source outside of this documentation.

a. For the difference between two estimates, one of which is a subclass of the other, use the tables directly where the calculated difference is the estimate of interest.

3. Means. The standard error of a mean depends upon the variability of the distribution on which the mean is based, the size of the sample, the sample design (for example, the use of households as a sampling unit), and the estimation procedure used.

An approximation to the standard error of the mean may be obtained as follows: compute the variance of the distribution on which the mean is based; multiply this value by five and divide the product by the total count of units in the distribution; obtain the square root of this quotient and multiply the result by the adjustment factor from table C that is appropriate for the characteristic on which the mean is based.

4. Medians. For the standard error of a median of a characteristic, it is necessary to examine the distribution from which the median is derived, as the size of the base and the distribution itself affect the standard error. An approximate method is given here. As the first step, compute one-half of the number on which the median is based (refer to this result as N/2). Treat N/2 as if it were an ordinary estimate and obtain its standard error as instructed above using tables A, B, and C. Compute the desired confidence interval about N/2. Starting with the lowest value of the characteristic, cumulate the frequencies in each category of the characteristic until the sum equals or first exceeds the lower limit of the confidence interval about N/2. By linear interpolation, obtain a value of the characteristic corresponding to this sum. This is the lower limit of the confidence interval of the median. In a similar manner, cumulate frequencies starting from the highest value of the characteristic until the sum equals or exceeds the count in excess of the upper limit of the interval about N/2. Interpolate as before to obtain the upper limit of the confidence interval for the estimated median.

A sample estimate and its estimated standard error may be used to construct confidence intervals about the estimate. These intervals are ranges that will contain the average value of the estimated characteristic that results over all possible samples, with a known probability. For example, if all possible samples that could result under the 1980 census sample design were independently selected and surveyed under the same conditions, and if the estimate and its estimated standard error were calculated for each of these samples, then:

(1)Approximately 68 percent of the intervals from one estimated standard error below the estimate to one estimated standard error above the estimate would contain the average result from all possible samples; and
(2)Approximately 95 percent of the intervals from two, estimated standard errors below the estimate to two estimated standard errors above the estimate would contain the average result from all possible samples.

The intervals are referred to as 68 percent and 95 percent confidence intervals, respectively.


The average value of the estimated characteristic that could be derived from all possible samples is or is not contained in any particular computed interval. Thus, we cannot wake the statement that the average value has a certain probability of falling between the limits of the calculated confidence interval. Rather, one can say with a specified probability or confidence that the calculated confidence interval includes the average estimate from all possible samples (approximately the complete-count value).

Confidence intervals may also be constructed for the difference between two sample figures. This is done by computing the difference between these figures, obtaining the standard error of the differences (using the formula given earlier) and then forming a confidence interval for this estimated difference as above. One can then say with specified confidence that this interval includes the difference that would have been obtained by averaging the results from all possible samples.

The estimated standard errors given on STF 3 do not include all portions of the variability due to nonsampling error that may be present in the data. The standard errors reflect the effect of simple response variance, but not the effect of correlated errors introduced by enumerators, coders, or other field or processing personnel. Thus, the standard errors calculated represent a lower bound of the total error. As a result, confidence intervals formed using these estimated standard errors may not meet the stated levels of confidence (i.e., 68 or 95 percent). Thus, some care must he exercised in the interpretation of the data on STF 3 based on the estimated standard errors.

For more information on confidence intervals and nonsampling error, see any standard sampling theory text.

1.The table shows that for [Anytown] out of all [329,571] persons aged 18 years and over, [12,524.] speak a language other than English at home. The procedure for obtaining the standard error of [12,524] will be demonstrated.

The unadjusted standard error for the estimated total is obtained from table A or from the formula below table A. In order to avoid interpolation, the use of the formula will he demonstrated here. BY- the formula, the unadjusted standard error, Se, is given by



The standard error of the estimated [12,524] persons aged 18 years and over who speak a language other than English at home is found by multiplying the unadjusted standard error, [247], by the appropriate adjustment factor. Table 2 of the STF 3 record for [Anytown] shows [89,452] as the unweighted sample count of persons. This figure is found to be roughly [19] percent of the l00-percent count of [470.816] persons shown in STF 3 table 3. Table C lists the adjustment factor for the characteristic "Language Usage and Ability to Speak English." The column that gives the range which includes [19] percent in sample shows the adjustment factor to be (I.31 for "Language Usage and Ability to
Speak English." Thus, the estimated standard error is x
or.

The estimated percent of persons 18 or older who speak a language other than English at home is [3.8]. From table B, the unadjusted standard error is found to be [0.l]. Thus, the standard error for the estimated percent of persons 18 or older who speak a language other than English at home is seen to be [1.3] x [0.l] = [0.13].

A note of caution concerning numerical values is necessary. Standard errors of percentages derived in this manner are approximate. Calculations can be expressed to several decimal places, but to do so would indicate more precision in the data than is justifiable. Final results should contain no more than one decimal place when the estimated standard error is one percentage point (i.e., 1.0) or more.

1. In the previous example, the standard error of the [12,524] persons, 18 and older in [Anytown] who speak a language other than English at home is found to be [321]. Thus, a 95-percent confidence interval for this estimated total is found to be

[12,524] - 3 ([321]) to [12,524] + 2 (1321))

or

[11,882] to [13,166].

One can say with about 95-percent confidence that this interval includes the actual value that would have been obtained by averaging the results from all possible samples.

The calculation of standard errors and confidence intervals will be illustrated when a difference of two sample estimates is obtained. For example, the number of persons in [Anyplace] aged 18 years and over who speak a language other than English at home is [12,500] and the total number of persons aged 18 years and over is [250,000]. Thus, the percentage of persons 18 years and over who speak a language other than English at home is [5] percent. The unadjusted standard error from table B is percent. The STF 3 record for [Anyplace] contains [49,000] as the unweighted sample count of persons in table 2 and [350,000] as the l00-percent count of persons yielding a percent-in-sample of [14] percent. From table C, the column that gives the range which includes [14] percent in sample, shows the adjustment factor to be [l.5] for "Language Usage and Ability to Speak English." Thus, the approximate standard error of the percentage (5 percent) is [O.1] x [1.5] = [0.15].

Suppose that one wishes to obtain the standard error of the difference between [Anytown] and [Anyplace] of the percentages of persons who were 18 years and over and who speak a language other than English at home.

The difference in the percentages of interest for the two cities is

[5.0] - [3.8] = [1.2] percent

Using the results of the previous example



The 95-percent confidence interval for the difference is formed as before.

[1.2] - 2 [0.20] to [1.2] + 2 [0.20]
or
[0.8] to [1.6]

One can say with 95-percent confidence that the interval includes the actual difference that would have been obtained by averaging the results from all possible samples.

The estimates which appear on STF 3 were obtained from an iterative ratio estimation procedure which resulted in the assignment of a weight to each sample person or housing unit record. For any given tabulation area, a characteristic total was estimated by summing the weights assigned to the persons or housing units in the tabulation area which possessed the characteristic. Estimates of family characteristics were based on the weights assigned to the family members designated as householders. Each sample Person or housing unit record was assigned exactly one weight to be used to produce estimates of all characteristics. For example, if the weight given to a sample person or housing unit h
The estimation procedure used to assign the weights was performed in geographically defined "weighting areas." Weighting areas were generally formed of adjoining portions of geography, which closely agreed with census tabulation areas within counties. Weighting areas were required to have a minimum sample of 400 persons. Weighting areas were never allowed to cross State or county boundaries. In small counties with a sample count of less than 400 persons, the minimum required sample condition was relaxed to permit the entire county to become a weighting area.

Within a weighting area, the ratio estimation procedure for persons was performed in three stages. For Persons, the first stage employed seventeen household type groups. The second stage used two groups: householders and non-householders. The third stage could potentially use 160 age-sex-race-Spanish origin groups. The stages were as follows:

Persons
Stage I - Type of Household
Group	Persons in Housing Units With a Family With Own Children Under 18.
1	2 persons in housing unit
2	3 persons in housing unit
3	4 persons in housing unit
4	5 to 7 persons in housing unit
5	8-or-more persons in housing unit
Group	Persons in Housing Units With a Family Without Own Children Under 18.
6-10	2 persons in housing unit through 8-or-more persons in housing unit
Group	Persons in All Other Housing Units
11	1 person in housing unit
12-16	2 persons in housing unit through 8-or-more persons in housing unit
17	Persons in group quarters
Stage II - Householder/Non-householder
Group
1	Householder
2	Non-householder (including persons in group quarters)
Stage III - Age/Sex/Race/Spanish Origin
Group	White Race
	Persons of Spanish Origin
	Male
1	0 to 4 years of age
2	5 to 14 years of age
3	15 to 19 years of age
4	20 to 24 years of age
5	5 to 34 years of age
6	35 to 44 years of age
7	45 to 64 years of age
8	65 years of age or older
	Female
9-16	Same age categories as groups 1 to 8
17-32	Persons Not of Spanish Origin
	Same age and sex categories as groups 1 to 16
33-64	Black Race
	Same age/sex/Spanish origin categories as groups 1 to 32
65-96	Asian and Pacific Islander Race
	Same age/sex/Spanish origin categories as groups 1 to 32
97-128	American Indian or Eskimo or Aleut Race
	Same age/sex/Spanish origin categories as groups 1 to 32
129-150	Other Race (includes those races not listed above)
	Same age/sex/Spanish origin categories as groups 1 to 32

Within a weighting area, the first step in the estimation procedure was to assign each sample person record an initial weight. This weight was approximately equal to the inverse of the probability of selecting a person for the census sample.

The next step in the estimation procedure was to combine, if necessary, the groups in each of the three stages prior to the repeated ratio estimation in order to increase the reliability of the ratio estimation procedure. For the first and second stages, any group that did not meet certain criteria concerning the unweighted sample count or the ratio of the complete count to the initially weighted sample count, was combined, or collapsed, with another group in the same stage according to a specified collapsing pattern. At the third stage, the "other" race category was collapsed with the "White" race category before the above collapsing criteria, as well as an additional criterion concerning the number of complete count persons in each category were applied.

As a final step, the initial weights underwent three stages of ratio adjustment which used the groups listed above. At the first stage, the ratio of the complete census count to the sum of the initial weights for each sample person was computed for each stage I group. The initial weight assigned to each person in a group was then multiplied by the stage I group ratio to produce an adjusted weight. In stage II, the stage I adjusted weights were again adjusted by the ratio of the complete census count to the sum of the stage I weights for sample persons in each stage II group. Finally, the stage II weights were adjusted at stage III by the ratio of the complete census count and the sum of the stage II weights for sample persons in each stage III group. The three stages of adjustment were performed twice (two iterations) in the order given above. The weights obtained from the second iteration for Stage III were assigned to the sample person records. However, to avoid complications in rounding for tabulated data, only whole number weights were assigned. For example, if the final weight for the persons in a particular group was 7.2, then one-fifth of the sample persons in this group were randomly assigned a weight of 8 and the remaining four-fifths received a weight of 7.

Separate weights were derived for tabulating the place of work and migration data items. The weights were obtained by adjusting the weight derived above for persons on questionnaires selected for coding by the reciprocal of the ED coding rate and a ratio adjustment to ensure that the sum of the weights and the complete count total population figure would agree.

The ratio estimation procedure for housing units was essentially the same as that for persons. The major difference was that the occupied housing unit ratio estimation procedure was done in two stages and the vacant housing unit ratio estimation procedure was done in one stage. The first stage for occupied housing units employed sixteen household type categories and the second stage could potentially use 190 tenure-race-Spanish origin-value/rent groups. For vacant housing units three groups were utilized. The stages for the ratio estimation for housing units were as follows:

Occupied Housing Units
Stage 1. - Type of Household
Group	Housing Units With A Family With Own Children Under 18
1	2 persons in housing unit
2	3 persons in housing unit
3	4 persons in housing unit
4	5 to 7 persons in housing unit
5	8-or-more persons in housing unit
Group	Housing Units With A Family Without Own Children Under 15
6-10	2 persons in housing unit through 8-or-more persons in housing unit
Group	All Other Housing Units
11	1 person in housing unit
12-16	2 persons in housing unit through 8-or-more persons in housing unit
Stage II - Tenure/Race and Origin of Householder/ Value or Rent
	Owner
	White race (Householder)
Group	Persons of Spanish Origin (Householder)
	Value of House
1	$ 0 -$ 9,999
2	$ 10,000 - $19,999
3	$ 20,000 - $ 24,999
4	$ 25,000 - $ 49,999
5	$ 50,000 - $ 99,999
6	$100,000 - $149,999
7	$150,000 or more
8	Other Owners
9-16	Persons Not of Spanish Origin
	Same value categories as groups 1 to 8
17-32	Black Race
	Same value - Spanish origin categories as groups 1 to 16
33-48	Asian and Pacific Islander Race
	Same value - Spanish origin categories as groups 1 to 16
49-64	Indian (American) or Eskimo or Aleut Race
	Same value - Spanish origin categories as groups 1 to 16
65-80	Other Race (includes those races not listed above)
	Same value - Spanish origin categories as groups 1 to 16
Group	Renter
	White Race
	Persons of Spanish origin
	Rent Categories
81	$ 1-$ 59
82	$ 60 - $ 99
83	$100 - $149
84	$150 - $199
85	$200 - $249
86	$250 - $299
87	$300 - $399
88	$400 - $499
89	$500 or more
90	Other Renter
91	No Cash Rent
92-102	Persons Not of Spanish Origin
	Same rent categories as groups 81 to 91
103-124	Black Race
	Same rent - Spanish origin categories as groups 81 to 102
125-146	Asian and Pacific Islander Race
	Same rent - Spanish origin categories as groups 81 to 102
147-168	American Indian or Eskimo or Aleut Race
	Same rent - Spanish origin categories as groups 81 to 102
169-190	Other Race (includes those races not listed above)
	Same rent - Spanish origin categories as groups 81 to 102
Vacant housing units
1	Vacant for Rent
2	Vacant for Sale
3	Other Vacant

The estimates produced by this procedure realize some of the gains in sampling efficiency that would have resulted if the population had been stratified into the ratio estimation groups before sampling, and the sampling rate had been applied independently to each group. The net effect is a reduction in both the standard error and the possible bias of most estimated characteristics to levels below what would have resulted from simply using the initial (unadjusted) weight. A by-product of this estimation procedure is that the estimates from the sample will, for the most part, be consistent with the complete count figures for the population and housing unit groups used in the estimation procedure.

As mentioned above, nonsampling error is present in both sample and complete count data. If left unchecked, this error could introduce serious bias into the data, the variability of which could increase dramatically over that which would result purely from sampling. While it is impossible to completely eliminate nonsampling error from an operation as large and complex as the 1980 census, the Bureau of the Census attempted to control the sources of such error during the collection and processing operations. The primary sources of nonsampling error and the programs instituted for control of this error are described below. The success of these programs, however, was contingent upon how well the instructions were actually carried out during the census. To the extent possible, both the effects of these programs and the amount of error remaining after their application will be evaluated.

The objective of the processing operation is to produce a set of statistics that describes the population as accurately and clearly as possible. To meet this objective, certain unacceptable entries were edited.

In the field, questionnaires were reviewed for omissions and certain inconsistencies by a census clerk or an enumerator and, if necessary, a followup was made to obtain necessary information. In addition, a similar review was performed by hand only when it could not be done effectively by machine.

As one of the first steps in editing, the configuration of marks on the questionnaire column was scanned electronically to determine whether it contained information for a person or merely spurious marks. If the column contained entries for at least two of the basic characteristics (relationship, sex, race, age, marital status, Spanish origin), the inference was made that the marks represented a person. In cases in which two or more basic characteristics were available for only a portion of the people in the unit, other information on the questionnaire provided by an enumerator was used to determine the total number of persons. Names were not used as a criterion of the presence of a person because the electronic scanning did not distinguish any entry in the name space.

If any characteristics for a person were still missing when the questionnaire reached the central processing offices, they were supplied by allocation. Allocations, or assignments of acceptable codes in place of unacceptable entries were needed most often when an entry for a given item was lacking or when the information reported for a person on that item was inconsistent with other information for the person. As in previous censuses, the general procedure for changing unacceptable entries was that was consistent with to assign an entry for a person entries for other persons with similar characteristics. Thus, a person who was reported as a 20-year-old son of the householder, but for whom marital status was not reported, was assigned the same marital status 3s that of the last son processed in the same age group. The assignment of acceptable codes in place of blanks or unacceptable entries, it is believed, enhances the usefulness of the data.

The editing process also includes another type of correction; namely, the assignment of a full set of characteristics for a person. When there was an indication that a housing unit was occupied but the questionnaire contained no information for all or most of the people, although persons were known to be present, a previously processed household was selected as a substitute and the full set of characteristics for each substitute person was duplicated. These duplications fall into two classes: (1) "persons substituted for mechanical failure," e.g., when the questionnaire page on which persons were listed was not properly microfilmed, and (2) "persons substituted for noninterview," e.g., when a housing unit was indicated as occupied but the occupants were not listed on the questionnaire.

Specific tolerances were established for the number of computer allocations and substitutions that would be permitted. If the number of corrections was beyond tolerance, the questionnaires in which the errors occurred were clerically reviewed. If it was found that the errors resulted from damaged questionnaires, from improper microfilming, from faulty reading by FOSDIC of undamaged questionnaires, or from other types of machine failure, the questionnaires were reprocessed.







¹ For person and family characteristics, derive this figure from the appropriate STF 3 data by dividing the unweighted sample count of persons (table 2) by the 100-percent count of persons (table 3). For household and housing unit characteristics, derive this figure by dividing the unweighted sample count of housing units (table 5) by the 100-percent count of housing units (table 6).

² The adjustment factor for this characteristic was calculated as if about one half of the questionnaires had been coded. Thus, the factor will provide a conservative estimate of the standard error in areas where more than one half of the questionnaires were, in fact, coded.

See "Language Usage and Ability to Speak English".

See "Housing Unit".

See "Farm Residence;" "Rent, Contract;" "Value".

Age at last birthday, i.e., number of completed years from birth to April 1, 1980, based on replies to a question on month and year of birth. This item was asked on a complete-count basis.

Because of the central importance of the data on age, the question contains redundancies. The age entry on the basic tape record is derived from the FOSDIC entries of quarter and year of birth. For those persons who do not provide this information but who do provide "age at last birthday," the census enumerator or clerk uses an equivalency table to mark the appropriate FOSDIC circles. The item "age at last birthday" is used only secondarily because of the tendency of some people, in reporting their ages, to round off to "0" or "5" (and to report even rather than odd numbers). The write-in entries of month and year of birth are requested because some people have difficulty with (and therefore skip) the FOSDIC marking system in this question.

Age is tabulated by single years of age and by many different groupings such as 5-year age groups. Basic records identify single years (and quarter years on sample basic records) to 112. Public-use microdata samples show single years and quarters to 99, and 100 years or more.

Persons 15 years old and over who had ever been married were asked the month and year of their first marriage. This item was asked on a sample basis.

Age at first marriage is computed as the difference between the date of first marriage and the date of birth. However, since both dates are recorded on census basic records only in terms of quarters, there is some imprecision in the result. For instance, a person born in September 1950 and married in July 1970 would have been recorded as born and married in the third quarter and aged 20 at first marriage, even though the person was actually only 19 at the time.

Public-use microdata include the quarter of marriage, as well as age in whole and quarter years, so that age at first marriage can be figured in terms of quarter years, and so that the interval between marriage and the birth of children can be calculated.

Derived from the age responses for the householders. (See the definition of householder under "Household Relationship.") Age and household relationship were determined on a complete-count basis.

The most frequent applications of age of householder in 1980 tabulations involve only two categories: under 65 years old and 65 years and over. More detailed categories appear among the housing tabulations, for example: less than 25 years, 25 to 29, 30 to 34, 35 to 44, 45 to 59, 60 to 64, and 65 years and over. Age of householder is also derivable from age tabulations cross-classified by household relationship (STF 2). Age of householder is derivable from basic records in single years, 15 to 112. Public-use microdata samples also show single years to 99, but group together householders 100 years and over.

See "Year Structure Built".

See "Group Quarters Type".

Presence of equipment with a refrigeration unit to cool air in occupied and vacant housing units. Evaporative coolers and fans or blowers not connected to a refrigerating apparatus are excluded, but refrigerating heat pumps are included. This item was asked on a sample basis.

Alaska Native villages constitute tribes, bands, clans, groups, villages, communities, or associations in Alaska which were listed in sections 11 and 16 of the Alaska Native Claims Settlement Act, public Law 92-203, or which met the requirements of the Act and which the Secretary of Interior determined were, on the 1970 census enumeration date (April 1), composed of 25 or more Alaska Natives. This list was reviewed and updated for the Census Bureau by the State of Alaska, prior to the 1980 census, to specifically identify only those entities that were legally recognized as Alaska Native villages.

Data summaries for Alaska Native villages are included in STF's 2B, 2C, 4B, and 4C, and reports PC80-1-B and -c and HC80-1-A and -B.

Population and housing counts for Alaska Native villages are scheduled to be included in a supplementary report (PCSO-S1 series). In addition, a population subject report (PC30-2 series) featuring additional data on Alaska Native villages is also planned. Data for each Alaska Native village can be derived from MARF, STF 1A, and STF 3A by identifying the ED or ED's that constitute the village, and summarizing the data should multiple ED's be involved. (NOTE: Eklutna Native Village is in a blocked area; therefore, data can be derived from block group (BG) summaries for the village.) Each Alaska Native village has been assigned a unique 3-digit code by the Bureau which appears in the reservation code field.

Alaska Native villages are identified on the Alaska subdivision maps in the PC80-1-B and HC80-1-A reports. Alaska Native villages are also shown on Metropolitan Map Series, place, and county maps. It should be noted that Alaska Native villages do not have boundaries that are defined by legal descriptions, and therefore the boundaries shown on the census maps are only indicative of the approximate extent of a village; for those that correspond to a city or census designated place, the limits of such a place are construed to coincide with the extent of the Alaska Native village.

See "Race".

See "Citizenship".

See "Language Spoken At Home".

See "Race".

American Indian reservations are areas with boundaries established by treaty, statute, and/or executive or court order. The reservations and their boundaries were identified for the Census Bureau by the Bureau of Indian Affairs (BIA) and State governments. Federal and State reservations are located in 33 States and may cross State, county, minor civil division/census county division, and place boundaries. In tabulations for reservations, tribal trust lands outside the boundaries of reservations (off reservation) are not included as part of the reservations (see below).

Preliminary evaluation of the 1980 census data suggest that counts for a few reservations may be subject to certain limitations or nonsampling errors. Although the various field and computer operations undergo a number of quality control checks to ensure accuracy of the data, available evidence indicates that nonsampling errors are substantial for a small number of reservations. For example, a few reservations have a relatively high substitution rate. A listing of reservations where characteristics for 20 percent or more of the persons or housing units in the 1980 Census were substituted are shown in PC80-1-B reports, Appendix D, "Accuracy of the Data."(For a fuller discussion of nonsampling errors, see the Users' Guide, chapter 6, "Data Limitations," report appendixes on "Accuracy of the Data," or the "Technical Information" section in tape technical documentation.) Additional evaluation of the counts for reservations will be done when more information is available and a fuller explanation will be presented in 1980 census special reports on the 4merican Indian population.

Each American Indian reservation was assigned a unique 3-digit code by the Bureau. Enumeration districts (ED's) and block groups (BGs) which are inside boundaries of reservations are designated with an "N" in the ED prefix field in tape files.

Data summaries for American Indian reservations are included in STF's 2B, 2C, 4B, and 4C, and reports PC80-1-B and -C and HC80-1-A and -3.

Population and housing counts for reservations are scheduled to be included in a supplementary report (PC80-S1 series). Also, a population subject report (PC80-2 series) presenting additional data on American Indian reservations is also planned. Summaries on tape and in PC80-1-B and HC80-1-A show data not only for the reservation totals, but also for parts of reservations that cross State or county boundaries. Reservation data can also be derived from MARF, STF 1A, and STF 3A by the addition of component ED or BG summaries. Maps outlining reservation boundaries are included in the PC80-1-B and HC80-1-A reports. Reservation boundaries are also shown on detailed Metropolitan Map Series, place, and county maps.

Entities known as "areas," "chapters," "districts," 'segments," or "communities," are associated with some American Indian reservations and were identified for the Census Bureau for the 1980 census by tribal governments or the Bureau of Indian Affairs. In a few cases, such subreservation areas extend beyond reservation boundaries or are located entirely outside the reservation (off-reservation). American Indian subreservations recognized for the 1980 census are identified by a unique 3-digit code.

Data for subreservations are not summarized in regular census tabulations; however, subreservation data can be obtained from the Census Bureau on a cost-reimbursable basis from special tabulations.

For further information regarding subreservation areas, please write Population Division, Racial Statistics Branch, Bureau of the Census, Washington, D.C. 20233.)

Some American Indian reservations have tribal trust lands in the vicinity of the reservation. The Bureau of Indian Affairs identified these areas for the 1980 census. Tribal trust lands are located outside the reservation boundary (off-reservation) and are associated with a specific reservation.

Population and housing counts for tribal trust lands are scheduled to be included in a supplementary freport (PC8041 series). Additional information for these areas may be included in special reports or unpublished tabulations. Also, such data can be obtained from the Census Bureau on a cost-reimbursable basis from special tabulations.

(For further information regarding the geography for tribal trust lands, please write to Population Division, Racial Statistics Branch, Bureau of the Census, Washington, D.C. 20233.)

A person's self-identified origin, descent, lineage, nationality group, or country in which the person or the person's parents or ancestors were born before their arrival in the United States. This item was asked on a sample basis.

This question was asked of persons regardless of how many generations their ancestors had been in this country. Persons were asked to write in the name of the group with which they most closely identify. Those who thought of themselves as having more than one origin were asked to write in their multiple ancestry, e.g., German-Irish. Instructions specified that religious groups were not to be reported as ancestry groups.

The open-ended write-in item on axes try was coded in census processing offices into a numeric representation using a code list containing over 400 categories. If a response was in terms of a dual ancestry, e.g., Irish-English, the person was assigned two codes, in this case one for Irish and one for English. Census basic record and public-use microdata files represent over 400 x 400 possible combinations. Selected three-ancestry combinations expected to be frequently reported were also coded, but, otherwise, whenever three or more ancestries are entered in a single response, only the first two were coded. Persons indicating two or more ancestries are shown in tabulations under "multiple ancestry" and may be counted more than once in tabulations of selected multiple-ancestry groups.

Most tabulations presenting counts of persons by ancestry show (a) the following single-ancestry groups: Dutch, English, French, German,
Greek, Hungarian, Irish, Italian, Norwegian. Polish, Portuguese,
Russian, (selected categories), Scottish, Swedish, Ukrainian, and other; (b) the number of persons reporting multiple ancestry, and the following selected multiple-ancestry groups: English and other group(s), French and other group(s), German and other group(s), Irish and other group(s), Italian and other group(s), and Polish and other group(s); and (c) ancestry not specified. Ancestry not specified includes nonresponses, also shown separately, as well as responses indicating religious groups, and unclassifiable responses. Only STF 4 presents more categories of ancestry than this at the State level or below.

Tabulations in STF 4 which present characteristics of specific ancestry groups at the State level or below present data for six single-ancestry groups--English, French, German, Irish, Italian, and Polish--and for four additional groups which vary from State to State. These four variable groups are the largest single- and/or multiple-ancestry groups in that State exclusive of (a) the six groups cited above, (b) all groups listed separately in the race and Spanish-origin questions, and (c) the category "American."

See "Units in Structure".

See "Labor Force Status".

See "Labor Force Status".

See "Race".

See "Value".

See "Rent, Contract".

The number of passenger cars available at home for the use of the members of the household, ascertained for occupied housing units. The term automobile includes station wagons, but excludes vans, pickups, or larger trucks. Cars rented or leased for one month or more, company cars, and police and government cars are also included if kept at home and used for nonbusiness purposes.

(Household members include lodgers or other nonrelatives living in the unit.) Dismantled or dilapidated cars or immobile cars used only as a source of power for some piece of machinery are excluded from this category. The statistics do not measure the number of automobiles privately owned or the number of households owning automobiles. This item was asked on a sample basis.

See "Puerto Rico and Outlying Areas".

The presence of bathroom facilities, ascertained for all occupied and vacant housing units. This question was asked on a sample basis.

The number of bedrooms, ascertained for occupied and vacant units. Bedrooms are rooms used mainly for sleeping, even if also used for other Purposes. Rooms reserved for sleeping such as guest rooms, even though used infrequently, are counted as bedrooms.

0n the other hand, rooms used mainly for other purposes, even though used also for sleeping, such as a living room with a sofa bed, are not considered bedrooms. A housing unit consisting of only one room, such as a one-room efficiency apartment, is classified, by definition, as having no bedroom. This item was asked on a sample basis.

See "Nativity and Place of Birth;" State Of Birth".

See "Race".

Normally a rectangular piece of land, bounded by four streets. However, a block may also be irregular in shape or bounded by railroad, tracks, streams, or other features. Blocks do not cross the boundaries of counties, census tracts, or block numbering areas (BNA's). They may cross place boundaries and the boundaries of minor civil divisions (MCD's). When blocks cross place boundaries and, in 20 States (see figure 5, column 3), when they cross MCD boundaries, separate statistical summaries are presented for each part of the block.

Census blocks are normally compact units, but there are important exceptions. For example, in some suburbs, houses cluster around cul-de-sacs. In these areas a census block may be fairly large since only those features that serve as the perimeter of an enclosed area are treated as block boundaries. Also, in those rural areas where they are numbered, blocks may include many square miles, depending on the frequency of intersections of roads, rivers, mountain ridges, or other physical features.



Census data are tabulated by block in all urbanized areas (UA's) and generally for some territory extending beyond the UA boundaries. Data also are tabulated by block in incorporated places with 10,000 or more inhabitants outside UA's, and in other areas which contracted with the Census Bureau for the preparation of block statistics. Places outside of UA's are included in the block statistics program if they met the 10,000 population criterion in the 1970 census, in official Bureau estimates through 1976, or in a special census taken on or before December 31, 1977. Block coverage for qualifying places is within boundaries as of January 1, 1980. Five States contracted for the preparation of block statistics for all of their territory, both urban and rural, not already in the block statistics program. These States are Georgia, Mississippi, New York, Rhode Island, and Virginia.

A block is identified by a 3-digit code which is unique within census tract or, where tracts do not exist, BNA. Since separate summaries are provided for the parts of a block split by a place boundary or, in 20 States, an MCD boundary, tape users often will need to specify the place or MCD code, along with other codes, to retrieve data for a block. Blocks are defined on detailed census maps: Metropolitan Map Series (MMS), Vicinity Map Series (VMS), place and county maps. The extent of block statistics coverage is reflected on maps by the presence of the 3-digit block number and the absence of ED boundaries and numbers.

On census maps, when a block boundary ignores a minor physical feature, such as a railroad track, a "fishhook" across the feature indicates that the block includes area on both sides of the feature. Alternatively, the separate parts of such a block may have identical block numbers, each followed by an asterisk.

The maps used for enumeration activities were, of necessity, obtained several years prior to the census and therefore do not reflect recently constructed streets. Only those features shown on the maps can serve as block boundaries.

Statistics were collected for approximately 2.6 million blocks in the 1980 census. Block statistics are included in PHC80-1 Block Statistics microfiche series and in file B of Summary Tape File 1 (STF 1B).

A combination of numbered census blocks that is a subdivision of a census tract or block numbering area (BNA) and is defined in all areas for which block statistics are prepared. (In areas where blocks are not numbered, ED's are used instead of BG's.)

BG's are not outlined on census maps, but are defined as that set of numbered blocks sharing the same first digit within a census tract or BNA. For example, Block Group "3" within a particular census tract would include any blocks numbered between 301 and 399. In most cases, the numbering would involve substantially fewer than 50 blocks, since gaps are occasionally left in the numbering; e.g. Block 312 might be followed by Block 316.

BG's are defined within census tract or BNA. They may cross, and be split by, the boundaries of minor civil divisions (MCD's) or census county divisions (CCD's), places, congressional districts, urbanized areas, and Indian reservations. When this occurs, statistical summaries (data records) are provided for each component or part. To avoid mistaking a component summary for a complete BG summary, users should carefully study census maps to note any BG's split by place, MCD or CCD, urbanized area, or Indian reservation boundaries. Congressional district (CD) boundaries are not shown on census maps, so the maps will not be of use in detecting BGs split by CD boundaries.

BG summaries observe boundaries of some areas (specifically, CCD's and, in 10 States, MCD's) which are ignored in summarizing data for the block statistics presentations in reports and on tape. As a result, it occasionally will be necessary to add BG components together to match the sum of blocks in the same hundreds series.

Statistics will he prepared for almost 200,000 BGs. 3G data, together with data for ED's, appear on STF's 1A and 3A, and in any corresponding microfiche. There are no printed data for BG's.

An area defined for the purpose of grouping and numbering blocks in block-numbered areas where census tracts have not been defined--typically, in nonSMSA places of 10,000 or more population and in contract block areas. BNA's do not cross county boundaries. They are identified by census tract-type numbers ranging from 9901.00 to 9989.99 which are unique within a county. While BNA numbers are similar to census tract numbers, BNA's are not census tracts and are not included in STF's 2 or 4.

BNAs maybe split by the boundaries of places, MCD's, and CCD's.

Statistical summaries appear in STF 1B and PHC80-1 Block Statistics microfiche series for the component parts of BNA's created when BNA's are split by the boundaries of places and, in 20 States, MCD's. (See figure 5, column 3.) Such component summaries appear in STF 1A and 3A when BNA's are split by the boundaries of CCD's in 20 States (see figure 5, column 1), and MCD's in 10 other States and Puerto Rico.

Determined for vacant units intended for year-round use. Boarded-up units have windows and doors covered by wood, metal, or similar materials to protect the interior and prevent entry. A single-unit structure or a unit(s) in a multi-unit structure may be boarded-up in this way. This item was ascertained on a complete-count basis.

See "Household Relationship".

See "County".

See "Industry".

See "Transportation to Work, Means Of".

See "Transportation to Work, Means Of;" "Vehicle Occupancy".

See "Automobiles Available".

See "County".

A statistical subdivision of a county, roughly comparable to a minor civil division (MCD). CCD's are defined in 20 States (see figure 5, column 1) which do not have MCD's suitable for reporting census statistics (i.e., the MCD's have lost their original significance, are very small in population, have frequent boundary changes, and/or have indefinite boundaries). CCD'S are established cooperatively by the Census Bureau and both State and local government authorities. They are generally defined by boundary features that seldom change and can be easily located, such as roads, rivers, and powerlines.

CCD boundaries are represented on detailed census maps, such as MMS/VMS sheets and county maps. In addition, CCD outlines appear at a small scale on maps published in several 1980 reports. CCD's in alphabetic sequence are assigned unique, incremental 3-digit numeric codes within counties.

Statistics for about 5,500 CCD's appear in STF's 1A, 2B, 3A, and (under tentative plans) 4B, and in PC80-1-A and -B and HC80-1-A reports.

A statistical subdivision of a "census area" or borough (county equivalent) in Alaska. Census subareas take the place of minor civil divisions (MCD's) or census county divisions (CCD's).

A small statistical subdivision of a county. Tracts generally have stable boundaries. When census tracts are established, they are designed to be relatively homogeneous areas with respect to population characteristics, economic status, and living conditions. Tracts generally have between 2,500 an3 8,000 residents. All standard metropolitan statistical areas (SMSA's) recognized for the 1980 census have census tracts. Most of these SMSA's are completely tracted, but seven SMSA's newly created as a result of the 1980 census include outlying counties which are not tracted. In addition, an estimated 3,000 census tracts have been established in 221 counties outside SMSA's. Five States and the District of Columbia are entirely tracted: Connecticut, Delaware, Hawaii, New Jersey, and Rhode Island. In all, there are over 43,300 census tracts for the 1980 census (including 465 in Puerto Rico).

Census tract boundaries are established cooperatively by local Census Statistical Areas Committees and the Census Bureau in accordance with guidelines that impose limitations on population size and specify the need for visible boundaries. Geographic shape and area size of tracts are of relatively minor importance. Tract boundaries are established with the intention of being maintained over a long time so that statistical comparisons can be made from census to census. Census tracts observe county lines and cover all of the territory within each tracted county. Within a county, tract boundaries may be split by other geographic boundaries.

Census tracts are identified by a 4-digit basic code and may have a 2-digit suffix, e.g., 6059.02. On tape, the decimal is implied.

Many census tracts do not have a suffix. In such cases, tapes give the 4-digit code followed by two blanks. Leading zeros in a tract number (e.g., 0025.02) do not appear on the maps (e.g., 25.02).

Tract numbers are always unique within a county and, except for the New York SMSA, are also unique within an SMSA. All valid census tract numbers are in the range 0001 to 9899.99; a number between 9901 and 9989.99 denotes a block numbering area (BNA).

Census tract boundaries are shown on all detailed census maps, such as place and county maps. In addition, census tract outline maps are being created for each SMSA and each tracted county outside SMSA's. Tract outline maps show only those streets and physical features which serve as census tract boundaries. In addition, the boundaries of places, MCD's, CCD's, counties, and States appear on tract outline maps.

Census tract data are presented in STF's 1A, 1B, 2A, 3A, and 4A, and in PHC80-2 Census Tracts reports. In STF 1A and 3A, tract data are presented in hierarchical sequence within place within MCD or CCD. In a case where a tract is split by place, MCD, or CCD boundaries, the tape files will have summaries for each of its parts. To get data for the whole tract, it will be necessary to add up the components. In STF 1B the situation is similar except that MCD boundaries are observed in only 20 States and Puerto Rico. (See figure 5, column 3.) MCD boundaries in the other 10 States with MCD'S and CCD boundaries in the remaining 20 States are ignored. In the major summaries for census tracts--those in STF 2A and 4A and in PXC80-2 Census Tracts reports--tract summaries observe the boundaries of places of 10,000 or more population. Separate summaries provide totals for split tracts.

An area of high land valuation characterized by a high concentration of retail businesses, service businesses, offices, theaters, and hotels, and by a high traffic flour. A CBD follows census tract boundaries, i.e., it consists of one or more whole census tracts. CBO's are identified only in central cities of SMSA's and other cities with a population of 50,000 or more, and are designated by local Census Statistical Areas Committees in consultation with the Census Bureau. However, some eligible cities have chosen not to participate in the CBD delineation program. CBD's generally do not extend beyond the boundaries of the city.

The CBD's now recognized were delineated for the 1977 economic censuses. The Bureau does not plan to prepare 1980 statistics for CBD's, but users may derive data by aggregating data for component census tracts or smaller areas. Records for such areas in the Geographic Identification Code Scheme report and on machine-readable 1980 files include a CBD code when the area is in a CBD.

See "Standard Metropolitan Statistical Area;" "Urbanized Area".

See "Household Relationship".

Total live births born to women 15 years old and over regardless of marital status. Respondents were instructed to include children born to the woman before her present marriage, children no longer living, children born to the woman who were still living in the home, as well as children away from home. This item was asked on a sample basis.

Typical presentations include categories for 10-year age groups: 15 to 24, 25 to 34, 35 to 44, and separately for ever-married women as well as for women regardless of marital status in the age group. Data are most frequently presented in terms of the aggregate number of children ever born to women in the specified category and in terms of the rate per 1000 women. For purposes of calculating the aggregate, the open-ended response category "12 or more" is assigned 1 value of 13.

See "Labor Force Status".

Classification of workers according to the type of ownership of the employing organization. Class of worker is generally tabulated for employed persons 16 years old and over, but it is also obtained for 15-year-olds and persons not currently employed who have worked since 1975, in which case the data refer to the person's most recent employer or business. The determination of class of worker is independent of occupation and industry classifications, but refers to the same job. These data were collected on a sample basis.

See "School Level;" "School Years Completed".

See "Group Quarters Type".

See "School Years Completed".

See "Occupation".

See "Owner Costs, Selected Monthly;" "Value".

See "Vehicle Occupancy;" "Transportation to Work, Means Of".

See "Kitchen Facilities, Complete".

See "Plumbing Facilities".

A type of ownership of an apartment in a building--or a house in a development--where ownership of common areas is shared. This item was asked on a complete-count basis.

One of the 435 State or sub-State areas from which persons are elected to the U.S. House of Representatives. Two sets of congressional districts are recognized in 1980 census products. Districts of the 97th Congress (1981-1982) are summarized on STF 1A and STF 3A. Districts of the 98th Congress (1983-1984) reflecting redistricting based on the 1980 census, are summarized on STF 1D and STF 3D and in series PHC80-4, Congressional Districts of the 98th Congress.

The PHC80-4 reports, issued by State, include a map of the State showing congressional district boundaries in relation to county outlines. More detailed maps follow showing selected congressional district boundaries in cases where the State map cannot delineate the congressional districts with sufficient clarity. These maps will be republished later in the Congressional District Atlas for the 98th Congress. Congressional district boundaries are not shown on detailed 1980 census maps.

See "Rent, Contract".

See "Kitchen Facilities, Complete".

See "Fuel".

See "Group Quarters Type".

See" Energy Costs, Monthly Residential;" "Owner Costs, Selected Monthly;" "Rent, Contract;" "Rent, Gross".

Foreign-born persons were asked to report their country of birth. Persons born in Puerto Rico, in an outlying area of the United States (e.g., Guam), or abroad of American parents (determined in the question on citizenship) are native and therefore are excluded from country-of-birth tabulations. These data come from the place-of-birth question, which also collected information on State of birth for natives, and was asked on a sample basis.

Foreign-born persons were asked to report their country of birth according to international boundaries as recognized by the U.S. government as of April 1, 1980. The respondent's entry was manually coded in census processing offices into a classification system consisting of over 250 foreign countries or groups of countries, as well as 22 categories for outlying areas of the United States. Most data presentations include 20 to 60 foreign-country categories. Census basic records and public-use microdata files separately identify 300 countries of birth.

See "Residence In 1975".

The primary political and administrative subdivision of a State. In Louisiana, such divisions are called parishes. In Alaska 23 boroughs and "census areas" are treated as county equivalents for census purposes. Several cities (Baltimore, Maryland; St. Louis, Missouri; Carson city, Nevada; and 41 Virginia cities) are independent of any county organization, and thereby constitute primary divisions of their States and are treated the same as counties in census tabulations.

County boundaries are shown on most census maps. A 3-digit Federal Information Processing Standards (FIPS) county code identifies each county uniquely within State. Counties are numbered in alphabetic sequence, with independent cities numbered separately at the end of the list.

There are 3,215 counties, and county equivalents (including 78 in Puerto Rico) recognized for the 1980 census. Tabulations for all counties appear in STF's 1 through 4, and in PC80-1-A, -B, and -C, HC80-1-A and -B, and PHC80-3 reports. Tabulations for counties of 30,000 or more inhabitants appear in STF 5.

See "County".

See "Census County Division;" "Census Subarea;" "Minor Civil Division".

See "Farm Residence".

See "Persons Per Room".

See "Housing Unit"

Presence of a physical, mental, or other health condition which has lasted 6 or more months and which limits or prevents a particular type of activity. Two types of disability were cited on the questionnaire--work disability, which is tabulated for noninstitutional persons 16 to 64 years old; and public transportation disability, which is tabulated for noninstitutional persons 16 to 54 years old and for noninstitutional persons 65 years old and over. This item was asked on a sample basis.

The term "health condition" refers to any physical or mental problem which has lasted for 6 months or more. A serious problem with seeing, hearing, or speech would be considered a health condition, whereas pregnancy or a temporary health problem such as a broken bone that is expected to heal normally would not be considered a health condition.

A census geographic division is one of the nine groups of States which are subdivisions of the four census geographic regions of the United States. (See figure 6.) Census geographic divisions are identified by a 1-digit code which is also the first digit of the 2-digit census geographic code for each State in the division.

See "Marital Status".

See "Vacancy, Duration Of".

See "Income Type".

A grouping of State economic areas (SEA's) which brings together those SEA's which are most closely related in terms of their economic and social characteristics. The areas were first defined following the 1950 census and updated after the 1960 census. In order to achieve such homogeneity, State boundaries are frequently crossed. The 510 SEA's are grouped into 121 ESR's. A 3-digit numeric code is assigned to each ESR. No data summaries will be prepared for ESR's, although the ESR code appears on the geographic records of the summary tape files.

See "Group Quarters Type".

In census usage, any of a variety of types of areas (e.g., election districts, precincts, legislative districts, wards) defined by States and local governments for purposes of elections. Under a cooperative Census Bureau/State program, the boundaries of election precincts and ED's or census blocks were drawn so as to be compatible in many States.

The Bureau prepared election precinct data for all or portions of 23 States; in some other States, users may aggregate block data to create election precinct statistics. The election precinct data appear in the P.L. 94-171 Population Counts tape file and on microfiche of that file.

See "Energy Costs, Monthly Residential;" "Fuel".

See "School Level".

Presence of a passenger elevator in the structure, ascertained for occupied and vacant housing units in structures with four or more stories or floors. Elevators are counted even if used largely, though not exclusively, for freight. Also included are stairway elevators and wheelchair lifts installed in structure of four or more stories. This item was asked on a sample basis.

See "Labor Force Status".

See "Class of Worker".

See "Air Conditioning;" "Energy Costs, Monthly Residential;" "Fuel;" "Heating Equipment".

The average monthly expense for fuels and utilities in occupied housing units. Fuels include oil, coal, wood, kerosene, and other fuels; utilities include electricity, gas, and water. Costs are recorded if paid by or billed to occupants, a welfare agency, relatives, or friends. Costs paid by landlords or included in condominium or cooperative fees are excluded. Also excluded are payments by occupants for fuel bills other than their own. Water and fuel costs are converted from a yearly basis as reported, to a monthly basis.

Utility and fuel costs are used primarily as components of "Gross Rent" and "Selected Monthly Owner Costs." since utilities included in rent payments are not recorded, residential energy cost data for renter-occupied units are of limited value for direct study. For that reason, separate fuel and utility cost figures are not issued in the more widely circulated census reports, but only on summary tapes. Basic record tapes and microdata show dollar amounts up to $999 for electricity, gas, and water, and to $9,999 for fuels. If the respondent used words or symbols such as more than" or some dollar amount with a "+", a dollar was added to the amount; if "less than" was used a dollar was subtracted. If the entry read "around," "approximately," or "about," the amount reported was used. These items were asked on a sample basis.

See "Language Spoken At Home and Ability To Speak English".

See "School Enrollment".

An area used in the 1980 census for (data collection activities and as a tabulation area where blocks are not present. ED's do not cross the boundaries of legal or statistical areas; for example, census tracts, MCD's/CCD's, places, counties, congressional districts, and States. Because of these constraints, they vary widely in population size, although they do not generally exceed a population of 1,600 in areas where the census was taken by mail, or a population of 1,000 in areas where the census was taken by conventional enumerator canvassing. The population limits are designed so that an ED generally represents a reasonable workload for one enumerator. About 1,000 jurisdictions in 47 States participated in a program for local definition of ED's. In areas without blocks, ED's are the smallest unit of census geography for which statistics are prepared.

ED boundaries are shown on MMS/VMS, place, and county maps in areas where there are no block numbers. ED's are identified by a 4-digit number (except that leading zeros, when they occur in ED numbers, do not appear on the maps). An ED number may be followed by a 1-letter alphabetic suffix. The suffix is used to identify subdivisions of ED's made during data collection and processing activities where the original ED proved to be too populous for an efficient work unit, or to accommodate a revision to a place or other boundary made after January 1, 1978 in mail-out/mail-back areas or January 1, 1979 in conventional census areas. An ED number may also have a l-letter prefix indicating that the ED is of a special type (e.g., an American Indian reservation), but the prefix is not necessary for unique identification of the ED. ED numbers do not repeat within a county. Any ED may be uniquely identified by accompanying its ED code with the 2-digit State code and 3-digit county code.

Statistics will be prepared for about 100,000 ED's. ED data, together with data for BG's, appear on STF's 1A and 3A and corresponding microfiche. In addition, ED data appear on STF 1B to complement the summaries for blocks. There are no printed data for ED's.

See "Air Conditioning;" "Heating Equipment;" "Telephone In Housing Unit;" "Vehicles Available".

See "Race".

See "Ancestry;" "Language Spoken At Home and Ability to Speak English;" "Nativity and Place of Birth;" "Race;" "Spanish Origin".

See "Labor Force Status".

See "Urbanized Area".

Two or more persons, including the householder, who are related by birth, marriage, or adoption, and who live together as one household; all such persons are considered as members of one family.

(Persons not in families and not inmates of institutions are classified as unrelated individuals.) Families are defined using responses to the complete-count household relationship question.

If the son/daughter of the person or couple who maintains the household and the son's or daughter's spouse and /or children are members of the household, they are treated as part of the householder's family. 1 roomer/boarder and his/her spouse who are not related to the person or persons who maintain the household, or a resident employee and his/her spouse living in are not counted as a family, but as individuals unrelated to the householder. Thus, a household can contain only one family for purposes of census tabulations.

A person maintaining a household alone, or two or more unrelated persons are regarded as a household but not as a family. Thus, some households do not contain a family.

Total money income received in calendar year 1979 by all family members 15 years old and over, tabulated for all families. Family income differs from household income by excluding income received by household members not related to the householder, persons living alone, and others in nonfamily households. (Income of these unrelated persons along with income of persons living in noninstitutional group quarters is tabulated as income of unrelated individuals 15 years old and over.) See the definitions of "Income In 1979" and "Income Type" for a discussion of the sources of income recorded, means, medians, limitations, and comparability.

In income tables for families, the lowest income group (e.g., less than $2,500) includes families that were classified as having no 1979 income as defined in the census. Many of these were living on income "in kind," savings, or gifts; were newly created families: or were families in which the sole breadwinner had recently died or left the household. However, many of the families who reported no income probably had some money income which was not recorded in the census. Family income is recorded on public-use microdata in $10 intervals up to $75,000 or down to a net loss of $9,990 or more.

Median and mean family income figures are based on all families, unlike mean or median income figures for persons 15 years old and over, which exclude persons with no income. This item was derived on a sample basis.
Historical comparability: Family income distributions have been tabulated in each census since 1950. Family income has been replaced by household income distributions in certain tabulations for 1980.

See also: "Income In 1979".

See "Household Relationship".

Families are classified by type according to sex of the householder and the presence of relatives, based on questions on sex and household relationship asked on a complete-count basis.

Presence of persons or housing units on farms. A farm is a place with $1,000 or more in sales of crops, livestock, or other farm products during the preceding calendar year. Farm residence is determined for both occupied and vacant housing units in rural areas. The question was structured to exclude units on city or suburban lots or on places of less than one acre. Urban areas are excluded through editing. Data are summarized in terms of housing units on farms or persons living on farms--not the number of farms. This item was determined on a sample basis.

See "Income Type".

See "Industry;" "Occupation".

See "Class of Worker".

See "Family Type;" "Sex".

See "Children Ever Born".

See "Owner Costs, Selected Monthly;" "Rent, Contract;" "Rent, Gross;" "Value".

See "Owner Costs, Selected Monthly".

See "Nativity and Place of Birth".

The types of combustible matter most often used for house heating, water heating, and cooking in occupied housing, units, tabulated separately. The term "house heating" applies to all types of structures, including apartment buildings. These items were asked on a sample basis.

See "Hours Worked Last Week;" "Hours Worked Per Week In 1979".

See "Stories in Structure".

See "Fuel".

See "Class of Worker".

See "School Level".

See "Rent, Gross".

See "Rent, Gross".

Persons in living arrangements, such as nursing homes or rooming houses, which are not households. Group quarters status was determined on a complete-count basis.

Two general categories of persons in group quarters are recognized.

Classification of institutions and noninstitutional quarters by the type of service provided, recorded on a sample basis for persons in group quarters. Note that statistics are provided primarily in terms of the number of persons residing in group quarters, not the number of group quarters (reported only in a subject report). See the definition for group quarters under Group Quarters, Persons In.

For those institutions which have multiple types of major service, usually general hospitals and Veterans Administration hospitals, inmates were classified by the type of care provided on their ward.

Type of heating equipment most often used, ascertained for occupied units and vacant units. Vacant units are classified by the type of heating equipment available for use by the intended occupants or that used by the previous occupants if the unit is without heating equipment. This item was asked on a sample basis.

The historic areas of Oklahoma consist of the former reservations which had legally established boundaries during the period 1900-1907. These reservations were dissolved during the 2- to 3-year period preceding the statehood of Oklahoma in 1907. The former reservation boundaries are used for planning purposes by tribes and the Federal government. In the census, the entire area encompassing the former reservations was identified (except, for parts inside urbanized areas as approximated in preparation for the 1980 census). Individual former reservations were not identified separately.

The historic areas of Oklahoma (excluding urbanized areas) were assigned a unique 3-digit code by the Bureau which appears in the reservation code field. Enumeration districts (ED's), block groups (BG's), and/or portions of BG's which comprise the historic areas (excluding urbanized areas) are designated with an "A" in the ED prefix in tape files for Oklahoma.

See "Tenure".

The number of vacant year-round units "for sale only as a percent of the total homeowner inventory, i.e., all owner-occupied units and all year-round vacant units for sale only. Vacant units that are seasonal or held off the market are excluded. This item was derived on a complete-count basis.

See also: "Vacancy Status".

The number of hours actually worked at all jobs during the reference week, ascertained for all persons who reported that they worked during that week. Lunch hours, sick leave, and vacation leave are excluded, but overtime or extra hours worked in the reference week are included. Therefore, the statistics do not necessarily reflect the number of hours usually worked or the scheduled number of hours. This item was asked on a sample basis.

The number of hours usually worked during those weeks the person worked in 1979, generally tabulated for persons 16 years old and over who worked in 1979. If the number of hours worked per week varied considerably during 1979, an approximate average was reported. This item was asked on a sample basis.

See "Fuel".

The person or persons occupying a housing unit. Counts of households, householders, and occupied-housing units are always identical in complete-count tabulations. In sample tables, the numbers may not always be the same because of differences in weighting sample data.

See also: "Household Relationship;" "Household Type;" "Housing Unit".

Total money income received in calendar year 1979 by all household members 15 years old and over, tabulated for all households. Household income differs from family income by including income received by (a) all household members 15 years old or over, not just those related to the householder, and by (b) persons living alone and in other nonfamily households. See the definitions of Income In 1979 and Income Type for discussions of sources of income recorded, means, medians, limitations, and comparability to other data bases.

In income tables for households, the lowest income group (e.g., less than $2.500) includes households that were classified as having no 1979 income as defined in the census. Many of these were living on income "in kind," savings, or gifts; were newly created households; or were households in which the sole breadwinner had recently died or left the household. However, many of the households who reported no income probably had some money income which was not recorded in the census. Household income is recorded on public-use microdata in $10 intervals up to $75,000 or down to a net loss of 39,990 or more.

Median and mean household income figures are based on all households, unlike mean or median income figures for persons 15 years old and over, which exclude persons with no income. This item was derived on a sample basis.

Relationship to the person in column 1 of the census questionnaire, ascertained from replies to a complete count question.

See "Household, Persons In;" "Persons in Unit".

Households are classified by type according to sex of the householder and the presence of relatives based on questions asked on sex and household relationship. This item was determined on a complete-count basis.

Presence of one or more of the conditions described below, determined for occupied housing units on a sample basis.

A house, apartment, mobile home or trailer, group of rooms, or single room occupied as a separate living quarter or, if vacant, intended for occupancy as a separate living quarter. Separate living quarters are those in which the occupants live and eat separately from any other persons in the building and which have direct access from the outside of the building or through a common hall.

The occupants may be a single family, one person living alone, two or more families living together, or any other group of related or unrelated persons who share living arrangements (except as described in definition of Group Quarters, Persons In). For vacant units, the criteria of separateness and direct access are applied to the intended occupants whenever possible. If that information cannot be obtained, the criteria are applied to the previous occupants. Both occupied and vacant housing units are included in the housing unit inventory, except that recreational vehicles, boats, caves, tents, railroad cars, and the like are included only if they are occupied as someone's usual place of residence. Vacant mobile homes are included provided they are intended for occupancy on the site where they stand. Vacant mobile homes on dealers' sales lots, at the factory, or in storage yards are excluded from the housing inventory. Housing unit status was determined on a complete-count basis.

The arithmetic difference between the total income of a family or unrelated individual and the appropriate poverty threshold, calculated for families and unrelated individuals below the poverty level. The aggregate income deficit provides an estimate of the amount of money which would be required to raise the incomes of all poor families and unrelated individuals to their respective thresholds at the poverty level. This item was derived on a sample basis.

Total money income received in calendar year 1979, ascertained on a sample basis for all persons 15 years old and over. Total income is the sum of amounts reported separately for income from wages and salaries; nonfarm self-employment, farm self-employment; interest, dividends, and net rental; Social Security; public assistance; and all other sources.

The figures represent the amount of income received before deductions for personal income taxes, Social Security, bond purchases, union dues, medicare deductions, etc.

Receipts from the following sources were not included as income: money received from the sale of property (unless the recipient was engaged in the business of selling such property, in which case, the net proceeds would be counted as income from self-employment); the value of income "in kind" such as free living quarters or food produced and consumed in the home; withdrawal of bank deposits; money borrowed; tax refunds; exchange of money between relatives living in the same household; and gifts and lump-sum inheritances, insurance payments, and other types of lump-sum receipts. The seven specific types of income recorded are further defined under Income Type.

Income in 1979 is reported in several different combinations. Household Income in 1979 and Family Income in 1979 are defined separately in this glossary. When entitled "Income In 1979," the data refer to the money income of Persons 15 years old and over. (Where family members received income jointly, appropriate amounts were to be apportioned among specific household members.) Income in 1979 is also tabulated for "unrelated individuals 15 years old and over," i.e., persons not accounted for in family income tabulations. Where a measure of income is to be interrelated with occupation or other work force characteristics, income other than earnings is generally excluded. See Income Type -- "Earnings."

Income is tabulated in intervals, for example, less than $5.000; $5.000 to 37,499; $7,500 to $9,999 ...$35.000 to $49,999; $50,000 or more. The highest income interval to be published in reports is $50,000 or more; on summary tape files the top interval is $75,000 or more. On census basic records incomes from each source are recorded in $10 intervals up to $100,000 and in $1.000 intervals from $100,000 to $999,000. Income amounts of $l, 000,000 or more are recorded as $999,500. Net losses up to $10,000 are also recorded in ten dollar intervals. Net losses of $10,000 or more are recorded as $-9995. High incomes are grouped together on public-use microdata, with "$75.000 or more as a single category, to avoid identification of individuals.

See "Family Income In 1979".

See "Household Income In 1979".

Classification of income in 1979 by the source from which it was received, ascertained on a sample basis for all persons 15 years old and over with income. See the definition of Income In 1979 for types of receipts which are not counted as income (e.g., tax refunds).

The kind of business or industrial activity in which the person was employed during the reference week or, if not employed, in which the person was most recently employed since 1975. Persons working at more than one job were instructed to describe the one at which they worked the most hours during the reference week. If the employer was engaged in more than one activity, the respondent was instructed to describe only the major activity at the place or facility where the person worked. Industry is most frequently tabulated for employed persons 16 years old and over, less often for the experienced civilian labor force, which includes both employed and experienced unemployed persons 16 years old and over. Industry data were also collected but are not tabulated for persons not currently in the labor force who have worked since 1975. Industry data are collected on a sample basis.

Responses were coded to one of 231 industry categories by specially trained industry and occupation coders in census processing offices.

Most large companies were included on a Company Name List (CNL) developed from the Census Bureau economic censuses. If the company entered in question 28a was found on the CNL, the coder assigned the industry code given by the CNL. If the company could not be found on the CNL, the coder used the industry description on 28b and 28c to determine the industry code. Only the code, i.e., none of the written-in information, is retained on census basic records and public-use microdata. Census industry categories are fully defined in the Classified Index of Industries and Occupations, PHC80-R3. Persons wishing to use the census system in coding other data bases may use the Alphabetical Index of Industries and Occupations, PHC80- R4. Major industry categories and important subdivisions are as follows:

Agriculture, forestry and fisheries

Mining

Construction

Manufacturing

       Nondurable goods

       Durable goods

Transportation, communications, and other public utilities

Wholesale trade

Retail trade

Finance, insurance, and real estate

Business and repair services

Personal services

Entertainment and recreation services

Professional and related services

       Health services

       Educational services

       Other professional and related services

Public Administration

See "Group Quarters, Persons In".

See "Owner Costs, Selected Monthly".

Presence of kitchen facilities in occupied and vacant housing units. This item was asked on a sample basis.

Persons 16 years old and over were classified as to their status in the labor force based on replies to several questions relating to work activity and status during the reference week. These items were asked on a sample basis.

Data on labor force status refer to the calendar week prior to the date on which respondents completed their questionnaires or were interviewed by enumerators. Since the week of enumeration was not the same for all persons, the reference week for labor force data is not entirely uniform. For many persons, however, the reference week for answering the 1980 census employment questions was the last week in March, 1980.

A series of items identified persons who worked in 1979 by the number of weeks worked and the number of hours usually worked per week, and persons who were unemployed in 1979 by the number of weeks unemployed. These data, collected on a sample basis, are tabulated for persons 16 years old and over regardless of current labor force status.

Persons who speak a language other than English at home were asked to report the language spoken, as well as their proficiency in English (see Language Usage and Ability to Speak English). This item was asked on a sample basis.

Respondents were instructed to report the language spoken most often, for persons speaking two or more non-English languages at home, or the first language learned, where the language spoken most often could not be determined.

The write-in entries of the language spoken were coded in census processing offices into 387 categories which arerecorded on basic records and public-use microdata files. Tables in PC30-1-C reports include the following categories:

English only, Chinese, French, German, Greek, Italian, Philippine languages, Polish, Spanish, other specified language, and unspecified language.

Data on languages spoken in the home are typically presented separately for persons 5 to 17 and 18 years old anti over. These data should not be interpreted as the number of people who are able to speak specified languages, since this question counts only persons who speak a language other than English at home.

The reported number of persons who speak a language other than English at home may be inflated slightly by a processing error. The total number of persons who speak a language other than English is inflated by approximately 0.4 percent nationwide. There is some geographic variation in the frequency of the errors, but no substantial spatial clustering has been discovered. Subsequent data products (STF 4, STF 5) will correct these errors, and thus may disagree with the estimates provided in STF 3.

Persons 5 years old and over are classified by whether they speak a language other than English at home, and, if so, by how well they speak English. Responses for persons under 5 are not tabulated. This item was asked on a sample basis.

See "Group Quarters, Persons In;" "Housing Units".

See "Family Type;" "Sex".

Persons 15 years old and over who had ever been married were asked whether they had been married more than once and, whether the first marriage ended because of the death of the person's spouse. Marital history is a construct which combines responses to these items with responses to the complete-count question on current marital status. The following items were derived on a sample basis.

All persons were asked whether they were "now married," "widowed," "divorced," "separated," or "never married." Marital status data are tabulated only for persons 15 years old and older. This item was asked on a complete-count basis.

Couples who live together (unmarried persons, persons in common-law marriages, etc.) were allowed to report tile marital status they considered the most appropriate.

See "Transportation To Work;" "Means Of".

See "Owner Costs, Selected Monthly;" "Value".

See "Residence In 1975".

A primary political and administrative subdivision of a county. MCD's are most frequently known as townships, but in some States they include towns, magisterial districts, and similar areas. A few counties have some territory not organized into MCD's; such "unorganized territory" is treated as one or more XCD's for census purposes.

MCD's are used for census purposes in 29 States (see figure 5, column 2).In 20 of the remaining States, CCD's are used in lieu of MCDs; in Alaska, census subareas are used. In the District of Columbia, quadrants are used. In Puerto Rico, ciudades, pueblos, and barrios are used.

The Census Bureau has assigned each MCD, alphabetically sequenced within county, an incremental, unique 3-digit numeric code. In addition, MCD's in 11 States (those noted in column 4 of figure 5) have a 4-digit "MCD sequence number" which allows MCD's to be sorted into alphabetical sequence within a State.

MCD boundaries are represented on all detailed census maps. In addition, MCD outlines appear on small-scale maps published in PC80-1-A and -B and HC80-1-A reports and in conjunction with the PHC80-2 series. There are about 26,000 MCD's recognized for the 1980 census.

Statistics for all MCD's appear in STF's 1A, 2B, 3A, and 4B, and in PC80-1-A and -B and HC80-1-A reports. In 20 States (specified in column 3 of figure 5), many MCD's serve as functioning general purpose governments, and these active MCD's are included in PHC80-3 Summary Characteristics for Governmental Units and Standard Metropolitan Statistical Areas. All MCD's in block-numbered areas of these States are included in PHC80-1 Block Statistics microfiche series and STF 18. Finally, in 11 States (all 9 States in the Northeast region, plus Michigan and Wisconsin), MCD data are published in a manner parallel to that of places of the same population size in tables of PC80-1-B and -C and HC80-1-A and -B. (See figure 5, column 4.)

See "Units at Address;" "Units in Structure".

The existence of a mortgage, deed of trust, contract to purchase, or similar debt on the property. Land contracts, contracts for deed, and assumption agreements are included. This item was ascertained for owner-occupied one-family houses on less than 10 acres, without a commercial establishment or medical office on the property. Mobile homes or trailers and condominium units were also excluded. This item was asked on a sample basis.

Selected monthly owner costs are usually reported separately for units with a mortgage and for units not mortgaged (i.e., owned free and clear) since housing costs are quite different for the two groups.

See "Puerto Rico and Outlying Areas".

The population is classified into "native" and foreign born" based on the State, foreign country, Puerto Rico, or outlying area of the United States where the person's mother was living at the time the person was born (not the location of the hospital if in a different State in the United States). This item was asked on a sample basis.

For purposes of the Census Bureau's Neighborhood Statistics Program, a neighborhood is a locally defined subarea of a locality. Neighborhoods must have official recognition, nonoverlapping boundaries, and a mechanism through which neighborhood residents may present their views on municipal matters.

See "Farm Residence".

See "Household Relationship".

The classification of all housing units as either occupied or vacant. This item was determined on a complete-count basis.

The kind of work the person was doing at a job or business during the reference week or, if not at work, at the most recent job or business if employed since 1975. Persons working at more than one job were instructed to describe the one at which the person worked the most hours during the reference week. Occupation is most frequently tabulated for employed persons 16 years old and over, and less often for the experienced civilian labor force, which includes both employed and experienced unemployed 16 years old and over. Occupation data were also collected but are not tabulated for persons not currently in the labor force who have worked since 1975. Occupation is not determined for persons in the Armed Forces. These data were collected on a sample basis.

The write-in responses to questions 29a and 29b were taken together to assign the respondent to one of 503 occupation categories, coded by specially trained industry and occupation coders in census processing offices. Only the code, i.e., none of the written-in information, is retained on census basic records and public-use microdata. Census occupation categories are fully defined in the Classified Index of Industries and Occupations, PHC80-R3. (Persons wishing to use the census system in coding other data bases may use the Alphabetical Index of Industries and Occupations, PHC80-R4.)

See "Units in Structure".

See "Household, Persons In".

See "Units in Structure".

See "Race".

See "Puerto Rico and Outlying Areas".

See "Persons per Room".

The sum of payments for real estate taxes, fire and hazard insurance, utilities, fuels, and mortgage. These data are tabulated for "specified owner-occupied" units, i.e., one-family houses on less than 10 acres without a commercial establishment or medical office on the property. The data exclude owner-occupied condominiums, mobile homes, and trailers.

Only selected monthly owner costs are included, since payments for maintenance and repair are excluded. Selected monthly owner costs are presented in tabulations comparable to those for gross rent since they are both measures of shelter costs) albeit for different universes.

The components of selected monthly owner costs are payments for the following items, all asked on a sample basis:

See "Tenure".

See "Tenure".

See "Race".

See "County".

See "Elevator in Structure".

See "Household Relationship".

The number of persons living in the housing unit. All occupants are counted--not just those related to the householder, but also any lodgers, roomers, hoarders, partners, wards, foster children, and resident employees who share the living quarters.

Figures for "persons in household" match those for "persons in unit" in tabulations based on complete-count data. In sample tabulations, they may differ because of the weighting process. The phrase "persons in household" is used for population tabulations, "persons in unit" for housing items. "One-person households" and "persons living alone" are synonymous.

See "Persons in Household".

A derived measure obtained by dividing the number of persons in each occupied housing unit by the number of rooms in the unit. The figures shown refer, therefore, to the number of housing units having the specified ratio of persons per room. For example, the number of units with 1.01 or more persons per room is the number of units occupied by more persons than there are separate rooms. This item was derived on a complete-count basis.

See also: "Rooms".

A concentration of population which may or may not have legally prescribed limits, powers, or functions. Most of the places identified in the 1980 census are incorporated as cities, towns, villages, or boroughs. In addition, census designated places (called "unincorporated places" in earlier censuses) are delineated for 1980 census tabulations. There are about 23,000 places recorded in the 1980 census. Places do not cross State boundaries.

The geographic location of the plant, office, store, or other establishment where the person worked most last week (see the discussion of reference week under Labor Force Status), ascertained for persons at work last week, including both civilian employed and Armed Forces at work, and tabulated for persons 16 years old and over. These data were obtained on a sample basis.

If the person worked at more than one location for the same employer (such as a grocery store chain or public school system), the exact address of the location or branch where the respondent worked most last week was requested. Persons working at more than one job were asked to report the location of the job at which they worked the greatest number of hours during the census week. Salespersons, delivery persons, and others who worked in several places each week were requested to give the address at which they began work each day, if they reported to a central headquarters. For cases in which daily work was not begun at a central place each day, the person was asked to report the exact address of the place where he or she worked the most hours last week.

Responses were coded in census processing offices but only for a sample of approximately one-half of the long-form questionnaires (a cost-saving measure). All entries were assigned codes which define the work location in terms of State, county, place of 2,500 or more (1,000 or more in Alaska and Hawaii) as estimated prior to the census, or in the Northeast region, minor civil division. For residents of SMSAs, place of work was coded further to tract and block (if in a blocked area) if the place was within the same SMSA or multi-SMSA commutershed.

Place-of-work tabulations vary considerably from one publication series to another. PC80-1-C reports furnish data for each of the following categories:

All workers

Place of work reported

Worked in area of residence

Worked outside area of residence

Percent of those reporting place of work

Place of work not reported

In these tabulations, the place of work is shown in terms of whether or not it is within the "area of residence," the definition of which varies with the geographic summary level. For instance, if a given column in a table presents data for a county, the place of work lines indicate the number of county residents who work inside and outside that county.

Census Tracts (PHC80-2) reports present up to 20 place-of-work categories for SMSA's, SMSA counties, places of 10,000 or more in SMSA'S, and census tracts as illustrated in the following list:

Inside SMSA

       Omaha, Nebr. central business district

       Remainder of Omaha city, Nebr.

       Remainder of Douglas County, Nebr.

       Bellevue city, Nebr.

       Remainder of Sarpy County, Nebr.

       Council Bluffs city, Iowa

       Carter Lake city, Iowa

       Remainder of Pottawattamie County, Iowa

Outside SMSA

       Lincoln city, Nebr.

       Remainder of Lancaster County, Nebr.

       Cass County, Nebr.

       Fremont city, Nebr.

       Remainder of Dodge County, Nebr.

       Washington County, Nebr.

       Mills County, Iowa

       Elsewhere

Place of work not reported

Up to 20 separate work locations are recognized in these PHC80-2 tabulations and on STF 4. The same 20 locations are used throughout each SMSA, but they vary from SXSA to SMSA and from county to county in nonmetropolitan areas.

Special tabulations can be prepared at user expense which make use of the additional detail available on census basic records. For instance, tabulations can be generated which show commuter flows by origin and destination in terms of census tracts within a given SMSA or multi-SMSA commutershed. Characteristics of workers by place of work can also be tabulated.

Public-use microdata "A" and "B" samples report place of work in the same terms as place of residence, i.e., States and "county groups" with 100,000 or more inhabitants. Within large SMSA's, individual counties and places over 100,000 are frequently identified as county groups making possible some analysis of commuting patterns by commuter characteristics. The "C" sample identifies place of work in central cities and in places in four size categories.

Presence of toilet facilities, bathing facilities, and piped water, ascertained for occupied and vacant housing units. This item was asked on a complete-count basis.

Families and unrelated individuals are classified as above or below the poverty level by comparing their total 1979 income to an income cutoff or "poverty threshold." The income cutoffs vary by family size, number of children, and age of the family householder or unrelated individual. Poverty status is determined for all families (and, by implication, all family members). Poverty status is also determined for persons not in families, except for inmates of institutions, members of the Armed Forces living in barracks, college students living in dormitories, and unrelated individuals under 15 years old. Poverty status is derived on a sample basis.

The 1980 census definition of poverty reflects revisions recommended by a Federal interagency committee in 1979 to a definition adopted in 1969. The index is based on the Department of Agriculture's 1961 Economy Food Plan and reflects the different consumption requirements of families based on their size and composition. It was determined from the Department of Agriculture's 1955 survey of food consumption that families .of three or more persons spend approximately one-third of their income on food; the poverty level for these families was, therefore, set at three times the cost of the economy food plan. For smaller families and persons living alone, the cost of the economy food plan was multiplied by factors that were slightly higher in order to compensate for the relatively larger fixed expenses of these smaller households. The poverty thresholds are updated every year to reflect changes in the Consumer Price Index (CPI). Cutoffs for 1979 income used in poverty statistics in the 1980 census are presented below. As an example, the poverty threshold for a family of four with two related children under 18 can be found in the chart below to be $7,356 in 1979.



Poverty thresholds are computed on a national basis only. No attempt has been made to adjust these thresholds for regional, State, or other local variations in the cost of living.

The poverty status of a person who is a family member is determined by the family income and its relationship to the appropriate poverty threshold for that family. The poverty status of an unrelated individual is determined by his or her own income in relation to the appropriate poverty threshold. Thus, two unrelated individuals living together may not have the same poverty status.

Households below the poverty level are defined as households in which the total income of the family or the householder of a nonfamily household is below the poverty level. The incomes of persons in the household other than members of the family or other than the householder in a nonfamily household are not taken into account when determining poverty status of a household.

Because the poverty levels currently in use by the Federal Government do not meet all the needs of the analysts of the data, variations of the poverty definition are available in terms of various multiples of the official poverty levels. The one most frequently tabulated is 125 percent of the poverty level, where a family or person may have up to 25 percent more income than normally allowed under the poverty threshold appropriate for the family size, etc.

See "Election Precinct".

See "Value".

See "Vehicle Occupancy".

See "Owner Costs, Selected Monthly".

See "Sewage Disposal".

See "Disability".

See "Water, Source Of".

In addition to the United States, the decennial census covers the Commonwealth of Puerto Rico and the outlying areas, including American Samoa, Guam, the Trust Territory of the Pacific Islands (including the Northern Mariana Islands which were legally part of the Trust Territory in 1980), the U.S. Virgin Islands, and certain other small islands over which the United States exercises sovereignty or jurisdiction. Questionnaire design and the questions asked were developed for Puerto Rico and each outlying area to accommodate local conditions. In the case of some small or military-occupied islands, enumerations were not conducted; only population counts obtained from U.S. Government records are published.

The geographic subareas for which statistics are reported vary. Some of those noted below are defined in this glossary; others will be defined in 1980 census reports for the areas.

• American Samoa: villages, district subdivisions, districts, and islands.
• Guam: census designated places and election districts.
• Northern Mariana Islands and the remainder of the Trust Territory of the Pacific Islands: census designated places, municipal districts, municipalities and islands, and administrative districts.
• Puerto Rico: blocks; ED's and BG's; census tracts and block numbering areas; zonas urbanas and aldeas; subbarrios; barrios, ciudades, and pueblos; municipios; and SMSA's and SCSA's.
• Virgin Islands: places, census subdistricts, and islands.
• Other islands: no subdivisions.

Data for Puerto Rico and its subdivisions will appear in reports and tapes in generally the same pattern as for States and their subdivisions. Data for outlying areas will appear in 1980 Census of Population, Volume 1, and 1980 Census of Housing, Volume 1, reports, and on STF's 1 and 3.

All persons wore asked to identify themselves according to the following race categories on the 1980 questionnaire: White, Black or Negro, American Indian, Eskimo, Aleut, Japanese, Chinese, Filipino, Korean, Asian Indian, Vietnamese, Hawaiian, Guamanian, Samoan, and Other. The "Other" category includes Malayan, Polynesian, Thai, and other groups not included in the specific categories listed on the questionnaire. This item was asked on a complete-count basis.

The concept of race as used by the Census bureau reflects self-identification by respondents; it does not denote any clear-cut scientific definition of biological stock. Since the 1980 census obtained information on race through self-identification, the data represent self-classification by people according to the race with which they identify themselves. For persons with parents of different races who could not provide a single response to the race question, the race of the person's mother was used; however, if a single response could not be provided for the person's mother, the first race reported by the person was used.

Counts of the population by race in complete-count tabulations are provisional. Final counts for race will be determined after the sample data have been processed. The sample counts will first appear on tape on STF 3 and in print in Characteristics of the Population, General Social and Economic Characteristics (PC80-1-C) reports.

Limited edit and review operations were performed during the complete-count operations; write-in responses were reviewed in an attempt to classify entries to specific categories, where appropriate. For instance, if the "Other" circle was marked with a write-in entry "Caucasian," then the response was recoded as White. (Additional examples are noted below.) However, all such cases were not identified in the complete-count processing. During the processing of sample questionnaires, a more thorough review and additional editing was done to resolve inconsistent or incomplete responses. Also, during the processing of sample questionnaires, write-in entries for the "Other" category were assigned specific codes, which is included on the person's basic record in the census sample detailed tape files.

Asian and Pacific Islander write-in entries, such as Indo-Chinese, Cambodian, or Polynesian, included in the "Other" category during 100-percent processing, are collectively tabulated and shown as "Other Asian and Pacific Islander" in the census sample tabulations; this group, "Other Asian and Pacific Islanders," will be included in the broader Asian and Pacific Islander category in all sample tabulations by race. This shift of "Other Asian and Pacific Islander" entries out of the "Other races" category in sample tabulations and the recoding of write-in entries in the "Other" category to specific categories where appropriate Will affect the comparability between complete-count and sample data for some groups.

In all cases where occupied housing units, households, or families are classified by race, the race of the householder, i.e., the person in column 1, is used (see Household Relationship for the definition of Householder). This item was determined on a complete-count basis.

Since some households include persons of more than one race, there may be minor differences in counts by race between (1) tabulations of "families by family size" or "households by persons in unit" where all persons regardless of their race are tallied according to tile race Of householder and (2) tabulations of "persons in families" or "persons in households" where all persons are counted according to their own race.

See "Owner Costs, Selected Monthly".

A large group of States, which is a first-order subdivision of the United States for census purposes. The four regions--Northeast, North Central, South, and West-are delineated in figure 6. Regions are identified by a l-digit code. Statistics for them appear in U.S. Summary reports in almost every publication series, and in STF's lC, 2C, 3C, and 4C. The census regions have no relationship to the 10 Standard Federal Administrative Regions.

See "Household Relationship".

The number of vacant units for rent as a percent of the total rental inventory--that is, all renter-occupied units and all year-round vacant units for rent. Vacant units that are seasonal or held off the market are excluded.

See also: "Vacancy Status".

The monthly rent agreed to, or contracted for regardless of any furnishings, utilities, or services that say be included. Rent is shown for occupied units rented for cash and vacant units for rent. For vacant units, rent is the amount for the asked unit at the time of enumeration, and is sometimes labeled "rent asked." Contract rent is tabulated for "specified renter occupied" units, which excludes one-family houses on 10 acres or more. Respondents were to report rent only for the housing unit enumerated and to exclude any rent paid for additional units or for business premises. The rent amount for the unit is to be reported even if paid for by someone outside the household, or for some reason, not paid. Respondents who do not pay rent monthly are asked to convert the sum to a monthly average. In the computation of aggregate and mean rent, $35 is taken as the average of the interval "less than $50," and $550 is taken as the average of the interval "$500 or more." This item was asked on a complete-count basis.

See "Tenure".

Contract rent plus the estimated average monthly cost of utilities (water, electricity, gas) and fuels (oil, coal, kerosene, wood, etc.)to the extent that these are paid for by the renter (or paid for by a relative, welfare agency, or friend) in addition to the rent. Gross rent is calculated for "specified renter-occupied" housing units, which excludes one-family houses on 10 acres or mops. Gross rent is sometimes preferred to contract rent in comparing costs since contract rent may or may not include utilities.

While public-use microdata show gross rent in dollar amounts (up to $l, 000), the data are not that precise. One reason is that the basic component, contract rent, is reported by the respondent in terms of intervals. To calculate gross rent, the respondent report is converted to a dollar amount by taking the midpoint of the interval; for example, $55 is used for the interval "$50 to $59" ($35 is taken as the value for "less than $50"; $550 is taken as the value for "$500 or more"). To that figure is added the reported average monthly cost of electricity and gas, and one-twelfth of the reported yearly cost of water and fuels. Gross rent data are typically tabulated in the same intervals as are used for contract rent. A unit classified as "no cash rent" in contract rent is also classified that way in gross rent, even if the unit's occupants pay for utilities themselves. Gross rent is calculated on a sample basis.

The usual place of residence 5 years before the census (i.e., on April 1, 1975), was asked on a sample basis of persons 5 years old or over. If residence was not in "this house" in 1975, the location was recorded in terms of State, county, and city, or foreign country. The same rules for usual place of residence apply to 1975 as to 1980. Persons such as college students or military personnel were to report the actual residence rather than the legal residence, if different. Residence in 1975 is used in conjunction with residence in 1980 to determine the residential mobility of the population.

See" Energy Costs, Monthly Residential".

The number of whole rooms intended for living purposes, not only in occupied housing units, but also in vacant units. These rooms include living rooms, dining rooms, kitchens, bedrooms, finished recreation rooms, enclosed porches suitable for year-round use, and lodger's rooms. Excluded are strip or pullman kitchens, bathrooms, open porches, balconies, foyers, halls, half-rooms, utility rooms, unfinished attics or basements, or other space used for storage. A partially divided room, such as a dinette next to a kitchen or living room, is a separate room only if there is a partition from floor to ceiling, but not if the partition consists solely of shelves or cabinets. This item was asked on a complete-count basis.

In the computation of aggregate and mean rooms, 10 is taken as the average of the interval "9 or more rooms."

See "Urban and Rural (Population)".

See "Farm Residence".

See "Farm Residence".

See "Value".

Persons 3 years old or over are classified as enrolled in school if they attended regular school or college at any time since February 1, 1980. This question was asked on a sample basis.