NLSY79

This section contains information on standard errors and design effects for the NLSY79 sample, briefly discussing how to use these two statistical factors. It then includes tables for the first round and for 1996 through 2022. Users interested in the intervening years should review the Technical Sampling Report and Technical Sampling Report Addendum.

Standard errors have been explicitly computed for a number of statistics based upon the entire NLSY79 sample (total, civilian, and military) and a number of sex or race subclasses. Standard errors for other statistics (defined over the entire sample or the subclasses) may be approximated with use of the DEFT factors given in the linked tables. Users who examine the tables will note that CHRR has calculated standard errors for different variables over time.

Approximate standard errors: Percentages

The following formula approximates a standard error of a percentage:

For example, for 1996 the appropriate DEFT factor for estimating a standard error of the percentage of Hispanic or Latino males who were high school dropouts is 1.17744 (see proportion column, row seven of Table 2. Deft factors for round 17, 1996). Assuming the calculated sample (P) equals 22.19 percent and the unweighted sample estimate size is 946, then:

To approximate the standard error of the corresponding projected population total (NP/100), calculate:

For example, if the projected total population base for Hispanic or Latino males is 1,030,861, the projected number of civilian Hispanic or Latino male high school dropouts is equal to NP/100 or 1,030,861 * 22.19/100 = 228,748. Thus, the approximate standard error for the total number of Hispanic or Latino male high school dropouts is:

Note: 1.5907 came from the previous calculation.

Approximate standard errors: Means

One can compute approximate standard errors for means as follows:

For example, for 1979 the DEFT factor for all Hispanics or Latinos is 1.45699 (see means column, row four of Table 1. Deft factors for round 1, 1979). To approximate the standard error of the mean number of years of education completed by this subclass, where the weighted element variance is .72955 and the sample size is 77, compute:

Design effects

Because the samples are multi-stage, stratified random samples instead of simple random samples, respondents tend to come in geographic clusters and clusters of persons tend to be alike in a variety of ways for a variety of reasons. (For more information on the sampling and screening process, users are referred to section on Sample Design & Screening Process in this guide.) For example, there may be cultural differences by locality or ecological differences in labor market conditions. Depending upon the degree of this homogeneity, the conventionally computed standard deviations for the variables, which assume a simple random sample, may be too small. However, by controlling the rate at which particular strata are sampled, multi-stage, stratified random samples can improve upon simple random samples. The ratio of the correct standard error to the standard error computed under the assumption of a simple random sample is known as the design effect. The technical sampling report for the NLSY79 (Frankel, Williams, and Spencer 1983) and its addendum (CHRR) provide design effects for the various strata.

A single design effect that can be broadly applied to regression analysis cannot be constructed. To illustrate the approximate size of design effects in regression analysis, a regression of rate of pay for the CPS job in 1979 was estimated using race, sex, marital status, and education as explanatory variables. Assuming each of the roughly 200 PSUs has the same number of respondents in the sample of 5,724 persons with observed wages, the design effect was calculated to be 1.52; that is, the true standard errors were larger than the naively computed standard errors by a factor of 1.52. When this exercise was repeated for rate of pay on the CPS job in 1986, the design effect had fallen to 1.37.

This reduction reflects the fact that mobility tends to mix the respondents more uniformly through the country, reducing the clustering of the sample. Many of the persons who started out in the same PSU will have moved to different areas and, hence, no longer share unobservable labor market conditions. These shared unobservable labor market conditions are likely responsible for the spatial correlation of the error terms which generate design effects. Thus, another advantage of longitudinal data is the lessening of design effects over time.

By examining the Geocode data for the NLSY79, it is possible to control for some of the environmental factors generating design effects or, if desired, to compute design effects based upon county or metropolitan area clusters which continue to be present. To facilitate study of design effects, scrambled PSU codes from the 1979 survey are available to persons with authorized access to the NLSY79 Geocode data.

The Technical Sampling Report and Technical Sampling Report Addendum also provide information on design effects.

Click below to view the DEFT and standard errors tables.

• Sample weights
• Custom weights
• Practical usage of weights
• Clustering adjustments

Sample weights

In each survey year a set of sampling weights is constructed. These weights provide the researcher with an estimate of how many individuals in the United States each respondent's answers represent. Weighting decisions for the NLSY79 are guided by the following principles:

1. individual case weights are assigned for each year in such a way as to produce group population estimates when used in tabulations
2. the assignment of individual respondent weights involves at least three types of adjustment, with additional considerations necessary for weighting of NLSY79 Child data

The interested user should consult the NLSY79 Technical Sampling Report (Frankel, Williams, and Spencer 1983) for a step-by-step description of the adjustment process. A cursory review of the process follows.

• Adjustment One. The first weighting adjustment involves the reciprocal of the probability of selection at the first interview. Specifically, this probability of selection is a function of the probability of selection associated with the household in which the respondent was located, as well as the subsampling (if any) applied to individuals identified in screening.
• Adjustment Two. This process adjusts for differential response (cooperation) rates in both the screening phase and subsequent interviews. Differential cooperation rates are computed (and adjusted) on the basis of geographic location and group membership, as well as within-group subclassification.
• Adjustment Three. This weighting adjustment attempts to correct for certain types of random variation associated with sampling as well as sample "undercoverage." These ratio estimations are used to conform the sample to independently derived population totals.

Sampling weight readjustments

Sampling weights for the main survey are readjusted to account for noninterviews each survey year. The readjustments are necessitated by differential nonresponse and use base year sample parameters for their creation, employing a procedure similar to that described above. The only exception occurs in the final stage of post-stratification. Post-stratification weights in survey rounds two and above have been recomputed on the basis of completed cases in that year's sample rather than the completed cases in the base year sample.

Custom weights

Users looking for a simple method to correct a single year's worth of raw data for the effects of over-sampling, clustering and differential base year participation should use the weights include each round on the data release. Unfortunately, while each round of weights provides an accurate adjustment for any single year, none of the weights provide an accurate method of adjusting multiple years' worth of data. The NLS has a custom weighting program which provides the ability to create a set of customized longitudinal weights. These weights improve a researcher's ability to accurately calculate summary statistics from multiple years of data.

The custom weighting program calculates its weights by first creating a new temporary list of individuals who meet all of a researcher's criteria. This list is then weighted as if the individuals had participated in a new survey round. The weights for this temporary list are the output of the custom weighting program.

There are two options for the custom weighting program on the Custom Weights for the NLSY79 page. The first option allows researchers to specify the particular rounds in which respondents participated. Researchers can also select if "The respondents are in all of the selected years" or can select if "The respondents are in any or all of the selected years." The second option allows users to input a list of respondent ids to get the appropriate weights for just that list. For example, this second option allows researcher to weight only those people who ever reported smoking cigarettes in any survey or weight only people who needed extra time to graduate from college.

Practical usage of weights

The application of sampling weights varies depending on the type of analysis being performed. If tabulating sample characteristics for a single interview year in order to describe the population being represented (that is, compute sample means, totals, or proportions), researchers should weight the observations using the weights provided. For example, to estimate the average hours worked in 1987 by persons born in 1957 through 1964, simply use the weighted average of hours worked, where weight is the 1987 sample weight. These weights are approximately correct when used in this way, with item nonresponse possibly generating small errors. Other applications for which users may wish to apply weighting, but for which the application of weights may not correspond to the intended result include:

Samples generated by dropping observations with item nonresponses

Often users confine their analysis to subsamples for which respondents provided valid answers to certain questions. In this case, a weighted mean will not represent the entire population, but rather those persons in the population who would have given a valid response to the specified questions. Item nonresponse because of refusals, don't knows, or invalid skips is usually quite small, so the degree to which the weights are incorrect is probably quite small. In the event that item nonresponse constitutes only a small proportion of the data for variables under analysis, population estimates (that is, weighted sample means, medians, and proportions) would be reasonably accurate. However, population estimates based on data items that have relatively high nonresponse rates, such as family income, may not necessarily be representative of the underlying population of the cohort under analysis. For more information on item nonresponse in the NLSY79, see the Item Nonresponse section of this guide.

Data from multiple waves

Because the weights are specific to a single wave of the study, and because respondents occasionally miss an interview but are contacted in a subsequent wave, a problem similar to item nonresponse arises when the data are used longitudinally. In addition, occasionally the weights for a respondent in different years may be quite dissimilar, leaving the user uncertain as to which weight is appropriate. In principle, if a user wished to apply weights to multiple wave data, weights would have to be recomputed based upon the persons for whom complete data are available. In practice, if the sample is limited to respondents interviewed in a terminal or end point year, the weight for that year can be used (for more information on weighting see the section on Sample Weights & Clustering Adjustments).

Regression analysis

A common question is whether one should use the provided weights to perform weighted least squares when doing regression analysis. Such a course of action may not lead to correct estimates. If particular groups follow significantly different regression specifications, the preferred method of analysis is to estimate a separate regression for each group or to use dummy (or indicator) variables to specify group membership.

Users interested in calculating the population average effect of, for example, education upon earnings, should simply compute the weighted average of the regression coefficients obtained for each group, using the sum of the weights for the persons in each group as the weights to be applied to the coefficients. While least squares is an estimator that is linear in the dependent variable, it is nonlinear in explanatory variables, and so weighting the observations will generate different results than taking the weighted average of the regression coefficients for the groups. The process of stratifying the sample into groups thought to have different regression coefficients and then testing for equality of coefficients across groups using an F-test is described in most statistics texts.

Users uncertain about the appropriate grouping should consult a statistician or other person knowledgeable about the data set before specifying the regression model. Note that if subgroups have different regression coefficients, a regression on a random sample of the population would not be properly specified.

Clustering adjustments

Researchers use NLSY79 data to estimate a variety of statistics. Since NLSY79 data come from a sample instead of data from every age appropriate individual in the U.S. the statistics produced are only estimates of the "true" national values. When researchers use a computer package to compute a statistic such as a mean or a regression coefficient, the program automatically provides a second set of statistics, such as the standard error, standard deviation, or t-statistic, which tells researchers how precisely the mean or coefficient is measured.

Details

Instead of randomly selecting individuals located anywhere in the U.S. during 1978, only a random selection of areas were selected. By randomly selecting a fixed number of small areas, interviewers reduced the amount of time they spent traveling for each interview. In this way, costs were lowered and the survey was fielded faster yielding data more quickly. Like all other national data sets that use clustering, NLSY79 data has many groups or bunches of respondents who share similar characteristics because they lived in the same neighborhood during 1978. This makes survey results appear more homogeneous, or similar, than actually found in the US.

Researchers can use two different approaches to correct this problem. The first approach uses the tables found in the NLSY79 Technical Sampling Report. For each survey round there is a table that lists the "Design Effects" or DEFT factors. These DEFTs give users a simple method for determining approximately how much they should increase their standard errors when trying to measure the precision of their estimates. Using the DEFT factors is a simple method of adjusting standard errors to account for clustering. However, when using specialized subsamples, these tables provide no guidance for users on how to adjust regression coefficients being based on calculations from only a small subset of NLSY79 variables.

The more general method is to correct for clustering by using a specialized software package. Two of the most widely used packages to adjust surveys for clustering effects are Stata, sold by the Stata Corporation and Sudaan, sold by RTI International. This section describes how to adjust for clustering using Sudaan. Sudaan is used to generate the DEFT factors found in the Technical Sampling Report.

Table 2 shows how adjusting for clustering affects a simple regression. Using the same 1998 data, a simple unweighted least squares equation was run with both SAS and Sudaan using net worth as the dependent variable and six independent variables. Three of these independent variables (BMI, income and age) take a wide range of values, while the remaining three variables (black, Hispanic or Latino, and female) take the value of 1 if the respondent has the particular characteristic and 0 otherwise.

The table shows that adjusting for clustering changes many of the standard errors and associated t-values. The biggest effect is seen on the income line. The uncorrected standard error increases from 0.06 to 0.19, resulting in the t-value falling from 44.37 to 13.87. Smaller changes are seen for the other variables. The intercept, age, and female standard errors all increase in size while the BMI, black, and Hispanic or Latino variables all end up with slightly smaller standard errors.

Overall, both examples show that adjusting for clustering effects is important. The next subsection shows what variables are needed to adjust for clustering. The section ends with the specific Sudaan commands used to create the tables in this chapter.

Key variables needed for clustering correction

Two variables are needed to adjust the data set for clustering. Both variables are found only on the Geocode data set and are placed there because researchers can use these variables to determine where each civilian respondent lived in 1978.

As discussed above, the NLSY79 is a multi-stage clustered sample. The clusters were created by first dividing the entire U.S. into Primary Sampling Units, or PSUs. These PSUs were defined by NORC and were composed of Standard Metropolitan Statistical Areas (SMSAs), entire counties when the counties were small, parts of counties when the counties were large, and independent cities. NORC randomly selected two different sets of PSUs for inclusion in the study, each of which by itself randomly represents the U.S. This selection of two sets of PSUs means the NLSY79 is composed of two replicates or strata. Within each is a random selection of PSUs. The replicate or strata that a respondent belongs to is found in the Geocode data set only and is labeled variable R02191.46, entitled "Within Stratum Replicate Of Primary Sampling Unit." This variable takes either the value 1 or 2, for either the first or second replicate.

The variable, containing the PSU is labeled R02191.45, and is entitled "Stratum Number For Primary Sampling Units." R02191.45 ranges in value from 1 to 120. Researchers who want to know which geographic areas correspond to particular values should look at Attachment 104 of the Geocode Codebook Supplement for the crosswalk table. Respondents with a PSU code of 52 to 70 are part of the military sample and do not have any known geographic location.

Using the key variables In Sudaan

The specific steps used to generate the tables above are covered in this section. While the tables were produced using the Windows Version 8.0 Standalone package, the steps and commands are similar for other versions of Sudaan. To adjust summary statistics such as means or regressions with Sudaan, the researcher needs to create three files: one containing the data, one telling Sudaan how to read the data, and one containing the specific commands. Any computer package can be used to create the data file. Data can even be written directly from NLS Investigator to a file. Figure 1 has the relevant portion of the SAS program used to create the data file used in Tables 1 and 2 above.

One of the key things to note is that the data are sorted by the PSU and replicate variables before being written to the file. For most operations, Sudaan requires the data to be in this order before processing.

The second file is the "label" file. This file is used to read the data into Sudaan. The label file, called "ObesitySudaanAdjustment.lab," is shown in Figure 2. The label file has five parts. The first column on the left is the variable's name, followed by a letter which tells Sudaan if the variable contains numeric or character data. The third and fourth columns contain the number of bytes (characters) taken up by the variable and the number of decimal places in the number. The last column contains the label. Sudaan expects the label file to follow a precise format with columns starting and ending in very specific places.

The third file is the set of commands used to run Sudaan. Many versions of Sudaan allow commands to be typed directly into the program so researchers are not forced to create command files. Figures 3 and 4 provide the Sudaan commands that were used to create Tables 1 and 2 above. Figure 3 has three sections. The top section below the "Proc Descript" command tells Sudaan where to find the raw data and what variable contains the basic survey weights. The nest command defines which variables contain the replicate and PSU information. The middle section, beginning with "Var," tells Sudaan which variables will have descriptive statistics created. The final section, beginning with "Print," specifies the types of output that are shown.

The first section of Figure 4 is similar to commands seen above in Proc Descript. The large difference is that the "weight" command has the reserved name "_ONE_" after it instead of the NLSY79 weight, "wght." Putting the "wght" variable after the weight command would cause Sudaan to run weighted least squares. By using "_ONE_" instead, Sudaan weights all variables with the same 1.0 value, resulting in Sudaan running unweighted least squares. The second part of the command, which begins with "Model," shows the exact regression to run.

There are six types of variables present in the NLSY79 data. Some are the raw answers provided by the respondent, while others are constructed. Types of variables include:

1. Direct (or raw) responses from a questionnaire or other survey instrument
2. Edited variables constructed from raw data according to consistent and detailed sets of procedures, such as occupational codes, KEY variables, and so forth
3. Constructed variables based on responses to more than one data item, either cross-sectionally or longitudinally, and edited for consistency where necessary, such as variables on the NLSY79 Supplemental Fertility File ("Fertility and Relationship History/Created" area of interest in NLS Investigator)
4. Constructed variables from other sources, such as the County & City Data Book information present on the NLSY79 Geocode data files
5. Variables provided by an outside organization based on sources not directly available to the user, such as the high school survey and transcript data, scores from the Armed Services Vocational Aptitude Battery, and so forth
6. Data collected from or about one universe of respondents reconstructed with a second universe as the unit of observation, such as variables on the NLSY79 Child File

The type of variable impacts:

• the title or variable description naming each variable,
• physical placement of each variable within the codebook, and
• location of a variable within a given area of interest.

Reference numbers

Every variable in the main NLSY79 data files has been assigned a reference number or identifier that determines its relative position within the data file and NLS documentation system. Persons contacting NLS User Services should be prepared to discuss their question or problem in relationship to the reference number(s) of the variable(s) in question.

Once assigned to variables within the NLSY79 data files, reference numbers remain constant through subsequent revisions of the files. Reference numbers are assigned sequentially, with variables referring to the first survey year having a lower reference number than those variables specific to the second year and so forth.

Occasionally variables are created in a year later than that in which the data were actually collected. These variables are frequently given a reference number with a decimal value that reflects the year in which the actual data were gathered rather than the year the created variable was constructed, for example, R01461.01. Beginning with the 1993 survey, decimals are also used to indicate that more than one variable has been derived from a single question.

Variable descriptions or variable titles

Each variable within NLSY79 main file data files has been assigned an 80 character summary title that serves as the verbal representation of that variable throughout the documentation.

Variable titles are assigned by CHRR archivists who endeavor, within the limitations described below, to capture the core "content" of the variable and to incorporate within the title:

1. "NLS Investigator areas of interest" that facilitate easy identification of related variables,
2. "Universe identifiers" that specify the subset of respondents for which each variable is relevant, and
3. "Reference periods" that indicate the specific period of time (e.g., survey year, calendar year) to which the data pertain for some variables. Universe identifiers and reference periods are discussed below.

Universe identifiers

If two ostensibly identical variables differ only in that they refer to different universes, the variable title will include a reference to the applicable universe by either appending in parentheses to each title the appropriate universe (Example 1) or by identifying the universe before the variable title (Example 2).

• Example 1: 'Did R Have Any Job since Last Int? (Unemployed or OLF) (1994)'
• Example 2: 'Female - Number of Children R Has Had since Last Interview'

Reference periods

Variable descriptions may include a phrase indicating the time period to which the data refer. When a date follows a verbal description of a variable and is preceded by the prepositional phrase "in 19XX," the date identifies the calendar year for which the relevant information was collected.

• Example: 'Received Income from Child Support in 1991?' This 1992 survey question refers to child support payments received in calendar year 1991.

Variables with similar content, such as information on respondents' labor force status, may have completely different titles, depending on the type of variable (raw versus created). In addition, such variables may be located within different NLSY79 areas of interest.

• Example 1: 'Employment Status Recode' (ESR), in 1979-98 and 2006, is the created or reconstructed version of the 'Activity Most of Survey Week' raw variable. The 'Activity' variable is derived from the first question of the full series of questions used by the Department of Labor (DOL) to obtain employment status; the title reflects questionnaire content. ESR, on the other hand, reflects the procedure used to recode the 'Activity' variable. This produces a constructed variable for all respondents based upon responses to the 'Activity' question and all other questions used by the DOL to obtain employment status. These other questions serve to qualify and refine employment status beyond the answer to the initial 'Activity' question.
• Example 2: NLSY79 raw fertility variables appear within the various "Children," "Birth Record," or "Birth Record xxxx" areas of interest while edited and constructed versions of these variables appear within the "Fertility and Relationship History/Created" area of interest.

Finally, different archivists, for a period of more than 20 years, have performed the task of assigning variable descriptions to data. While every effort has been made to maintain consistency, users may find some differences in variable title and area of interest assignment.

New variables created by researchers

Researchers sometimes use the NLS public datasets to generate a new variable to use in their research. In some cases, researchers like to make that new variable publicly available (through their own data repository) so that it can be easily accessed for follow-up studies. This is permissible as long as researchers are using public NLS data (rather than restricted) and that they make it clear they are the author of the variable rather than the NLS team.

The primary variables found within the main data set are derived directly from survey instruments, such as questionnaires, household interview forms, and so forth. This section describes each of the NLSY79 instruments in the order that they appear in the following list.

Types of NLSY79 survey instruments and user aids

• 1978 Household Screener; Household Interview Forms
• Interviewing Aids
  • Face Sheet
  • Information Sheet
  • Children's Record Forms (CRF)
• Questionnaires
• Questionnaire Supplements
  • 1980 Illegal Activities Form J
  • Employer Supplements (ES)
  • 1983 Fertility Supplement
  • Confidential Abortion Forms
  • 1988, 1992, 1994, and 1998 Drug Use Supplement
  • 1988 Childhood Residence Calendar
• Supplemental data collections
  • High School Survey
  • 1980-1983 Transcript Surveys
  • ASVAB
• Interviewer Reference Manuals (Q by Qs) and CAPI Help Information

This section also explains the conventions used in the NLSY79 documentation system to identify questionnaire items from some of the primary survey instruments. An additional document, the interviewer reference manual, provides background information on specific survey instruments.

A unique set of survey instruments has been used during each survey year to collect information from respondents. The term "survey instrument" is used to refer to:

1. the questionnaires that serve as the primary source of information on a given respondent
2. questionnaire supplements fielded during select survey years that contain additional sets of questions
3. documents such as the household interview forms or household record cards that collect information on members of each respondent's household

Users should be aware that, while the source of the majority of variables in the main NLSY79 data files is the questionnaire or one of the other survey instruments, certain NLSY79 variables are created either from other NLSY79 variables or from information found in an external data source (see Types of Variables).

Household information

Each NLSY79 interview includes the collection of information on the members of each respondent's household. For NLSY79 respondents, such household data are collected prior to the administration of the main questionnaire and for many years used separate survey instruments called the Household Interview Forms. Both the instruments used for the yearly household data collection and the household screening instruments that were used to draw the samples of respondents are described below.

NLSY79 1978 Household Screener and Interviewer's Reference Manual

This document (fully titled NLSY-National Longitudinal Survey of Labor Force Behavior Interviewer's Manual-Household Screening, NORC 1978) contains detailed information on the 1978 screening of households conducted by NORC from which the civilian youth samples (the cross-sectional and supplemental samples) were drawn. It provides a copy of the short 25-question screener, question-by-question specifications for administering the form, and a sample completed screener. Most of the information collected on each respondent during the screening is presented within the data set. The screener is the source for important data such as the sex and race or ethnicity variables that were used to assign each respondent to a specific NLSY79 subsample, as well as the relationship codes (for example, brother, sister, husband, wife) that allow researchers to identify related NLSY79 respondents who shared a household at the time of the screening.

Question numbering

Question numbers for the 1978 screener were arbitrarily assigned by NORC using an artificial questionnaire section number that followed the last section of the 1979 questionnaire ("Section 25" for all screener variables) even though the actual administration of the screener preceded that of the 1979 questionnaire.

Users should note that screener questions are identified within the documentation as 1979 variables even though these data were collected during 1978. Most variables from the screener use the phrase HOUSEHOLD SCREENER at the beginning of the variable title, appear physically within the codebook after the 1979 household record series, and have been placed within the "1978 Screener" and "Household Record" areas of interest.

Household interview forms

Yearly household information for the NLSY79 is collected from either the respondent or the head of household prior to the administration of the main questionnaire. NLSY79 Household Interview Forms are used to:

1. enumerate all persons currently living in the respondent's household
2. record information about each person's age, highest grade completed, work experience in the past year, and relationship to the respondent
3. collect, during the 1979-1986 surveys, certain family income information

Information on household members is collected using the questions on the Household Interview Forms; however, much of the information is actually recorded on the "Household Enumeration" section of the Face Sheet discussed below.

During the 1979-1986 interviews, different versions of the Household Interview Forms were administered depending upon the type of residence of the respondent. Version A was used if the respondent was living with his or her parents (or in-laws), in which case the interview was conducted with the respondent's parents (or in-laws) in order to gather information on household income sources. Version B was used if the respondent was living in group quarters, such as a dormitory or the military, or in temporary facilities, such as a hospital or prison, and was administered to the respondent. If the respondent had a permanent residence elsewhere, the household interview gathered information about that household. Version C was administered to the respondent if he or she was living in his or her own dwelling unit, military family housing, an orphanage, a religious institution, or other individual quarters or was the head of a family unit. Table 1 in the Household Composition section of depicts, by survey year, the universe and residential unit(s) specific to each form.

During the first eight survey rounds, many respondents were younger than 18 and living with their parents; thus, Version A was frequently used. Beginning with the 1987 survey, all respondents were 21 or older and living predominantly on their own; consequently, the household interview forms were consolidated into a single version. For 1979-1986, these forms appear as separate documents. Beginning with the 1987 interview, household interview questions were incorporated within each year's questionnaire. Some variation in administration of these forms has occurred over survey years. Users should refer to each survey year's Interviewer's Reference Manual for more information.

Interviewing aids

Certain instruments used during fielding of the NLSY79 provide researchers with interview- and respondent-specific information that appears as variables within the NLSY79 data files.

Face Sheet

Immediately prior to fielding, a Face Sheet is computer-generated for each respondent and forwarded to the interviewer assigned to that case. The Face Sheet contains:

1. various items of respondent-specific information (name, address, phone number)
2. information about each member of the household or family unit as of the last interview (full name, sex, relationship to youth, education, and whether the household member worked during the year), generated from the most recent administration of the Household Interview Forms
3. a historical overview of previous interview rounds (whether the respondent refused to be interviewed, the respondent was interviewed after initially refusing, the interview was complete or incomplete, and so forth)
4. for the 1980-1986 survey years, information on the version of the Household Interview Form that was used in the previous interview

This information is used to alert the interviewer and field manager to potential problems, assist them in preparing a successful location and fielding strategy, and provide details necessary to conduct an efficient interview, such as a listing of previous employers. Information about the respondent's household and family unit from each survey year's Face Sheet can be found by searching the "Household Record" area of interest with NLS Investigator. Sample Face Sheets for most survey years can be found in the various Interviewer Reference Manuals.

Information Sheet

This document contains data on the respondent from the previous interview that will be referred to and used to update information during the interviewing process. Items found on this document include marital status, high school completion status, university last attended, names of previous employers, training program enrollment, and pregnancy status. This information enables the interviewer to accurately route the respondent through the relevant sections of the questionnaire and provides on-the-spot reconciliation of earlier errors. Information Sheet items appear within the NLSY79 data set ("Last Interview Information" area of interest in NLS Investigator). Beginning with the 1993 interviews, the information sheet is incorporated into the CAPI instrument. Sample Information Sheets can be found in the Interviewer Reference Manuals. In CAPI surveys, information sheet data are stored electronically on the interviewer's laptop and accessed by the survey program during the interview; no paper information sheet is used.

Children's Record Forms (CRF) (1985-1992)

This interviewing aid containing information on biological (collected each survey) and nonbiological (that is, adopted or step-; collected biennially) children was used in the 1985-1992 surveys to:

1. provide identification numbers, names, dates of birth, sex, and deceased/adopted status for each child
2. identify special sections of the main questionnaire (such as immunization, feeding, and so forth) that needed to be administered for particular children

Sample Children's Record Forms can be found in the Interviewer's Reference Manuals. Beginning with the 1993 interviews, this form is incorporated into the CAPI instrument. As with information sheets, these data are automatically accessed by the survey program during CAPI interviews, so the hard copy CRF is no longer needed.

Questionnaires

There are separate and distinctly different questionnaires for each survey year of the NLSY79. Each questionnaire is organized around a set of topical subjects, the titles of which usually appear on either the first page of each section of the questionnaire or as a header.

NLSY79 questionnaires record:

1. interview dates
2. responses to the topical survey questions (see discussion below)
3. locating information which will assist NORC in finding the respondent for the next interview
4. interviewer remarks on such topics as the race and sex of respondent, language in which the interview was conducted, interviewer's impressions, and so forth

Show cards

These are interviewing aids used in conjunction with the questionnaire and list the possible response categories for selected questions. Show cards help the respondent keep the more complicated response categories in mind.

NLSY79 questionnaires explore the following core topics:

• current labor force status
• jobs and employers
• work experience and attitudes
• training
• assets and income
• family background
• marital history
• fertility
• regular schooling
• military service
• health

Additional sets of questions have been fielded during select survey years on such topics as:

• childcare
• alcohol use
• drug use
• job search methods
• educational/occupational aspirations
• school discipline
• pre-and post-natal health behaviors
• delinquency
• childhood residences

During the 1979-1992 paper-and-pencil (PAPI) interviews, questionnaires and other survey instruments were preprinted paper products used during fielding. With the advent of computer-assisted interviewing (CAPI) in 1993, the "questionnaire" became a series of visual screens that not only told the interviewers what questions to ask but provided helpful instructions on how to administer the interview. Separate supplemental documents such as the job-specific Employer Supplements were integrated into the electronic main questionnaire. NLSY79 CAPI questionnaires incorporate some helpful elements of the traditional codebook, with reference numbers assigned to variables and greater specificity on coding and universes provided within each codeblock.

Question numbering

The conventions used to assign question numbers within the NLSY79 documentation system vary by survey year and are based on various combinations of the questionnaire section number, the question number, or the deck and column numbers (Table 1). Users can locate a variable within the codebook--which represents each question fielded in the same order as it appears within the questionnaire--by finding the question number which appears (in parentheses) to the right of each reference number.

Deck and column numbers are vestigial items that were used to locate the data when it was input on punch cards. The deck numbers are printed at the upper right hand corner of each page in the survey instruments and at the beginning point for each new deck for the 1980 through 1992 instruments. The column numbers are printed to the left of the response categories. If the variable contains more than one digit, the column reference is to the starting column for that variable. 

Questionnaire supplements

Separate instruments called "supplements" have been used since the onset of the NLSY79 to administer distinct sets of questions. The NLSY79 has made extensive use of supplements for collecting information from separate universes such as schools or children or for administering confidential sets of questions on illegal activities or abortion. The following section describes each supplemental instrument used for the NLSY79. The use of such separate supplements has diminished with CAPI-administered interviews. In the main youth and young adult instruments, all supplements are now incorporated as electronic modules in a questionnaire. Children still use multiple supplements, one self-report, one interviewer-administered, and one completed by the mother.

Illegal Activities Form J (1980)

This confidential questionnaire supplement, administered during the 1980 survey, contains a series of questions designed to collect information on the extent of respondents' participation in various delinquent and criminal activities such as:

• skipping school
• alcohol/marijuana use
• vandalism
• shoplifting
• drug dealing
• and robbery

This series supplements those on reported contacts with the criminal justice system collected within the main questionnaire.

Employer Supplement

Information about each employer for whom a NLSY79 respondent has worked since the last interview has been collected since 1980. One Employer Supplement is administered for each employer and contains questions about gaps when the respondent was not working, the number of hours worked, the type of work done, and the wages earned at that job. Note: Comparable information for the 1979 survey can be found in the "On Jobs" section of the main questionnaire and within the separate single sheet 1979 Employer Flap. Beginning with the 1993 CAPI interviews, all employer supplement questions appear within the body of the main questionnaire.

Question numbering

Five numbering systems have been used to identify questionnaire items within the Employer Supplement (Table 2). Although data from up to 10 jobs are collected, the main data set includes information on only the first five jobs since few individuals work at more than five jobs between interviews. Data on all ten jobs are used to construct a series of summary variables for hours and weeks worked; see the Labor Force Status, Time & Tenure with Employers, and Work Experience sections for more information.

Fertility Supplement (1983)

Respondents (both male and female) who were not interviewed during 1982 were administered a special set of supplementary fertility questions during the 1983 survey. The Fertility Supplement was designed to collect complete fertility data, including all live births for males and females, and all pregnancy losses and contraception between pregnancies for females. For those not interviewed in 1982, these questions replaced the fertility questions found in Section 10 of the 1983 questionnaire.

Confidential Abortion Forms

Biennially beginning in 1984, female NLSY79 respondents have completed a short confidential abortion form which elicited information on the number and dates of each abortion. Copies of these supplementary questions are provided within the survey instrument sets. The 1984 form also collected information on the dates that respondents left school prior to 1979 if leaving school was associated with early childbearing. Beginning in 2002, the abortion form was included in the main instrument. 

Drug Use Supplement (1988, 1992, 1994, and 1998)

The 1988 supplement contains the confidential set of drug use questions which were, through a random assignment process, self-administered by the respondent in half of the cases and administered by the interviewer in the other half. Questions were asked on age at first use of marijuana and cocaine, extent of lifetime and most recent use, and method(s) practiced in using cocaine. The 1992 and 1994 supplements contain the confidential set of questions on respondents' use of cigarettes, alcohol, marijuana, cocaine, or other drugs. Users should note that while the 1988 and 1992 supplements are bound as separate booklets, the 1994 and 1998 supplements are bound with the main questionnaire.

Childhood Residence Calendar (1988)

The 1988 questionnaire contained a special section detailing the living arrangements of respondents from birth through age 18. The Childhood Residence Calendar, the interviewing aid used to collect these data, depicts for each year of life the type of parent (biological-, adoptive-, or step-) with whom each respondent lived for at least four months and, for those ages when he or she was not living with a parent, in what other arrangements the respondent resided, such as, with grandparents, foster parents, friends, or in a children's home, detention center, or other institution.

Supplemental data collections

High School Survey (1980)

A supplemental survey of the last secondary school attended by civilian NLSY79 respondents was conducted in 1980. This survey gathered information on each school's grading system, course offerings, dropout rate, student body composition, and faculty characteristics, as well as respondent scores from a variety of intelligence and aptitude tests. Copies of the high school survey instruments, the "School Questionnaire" and the "Student's School Record Information" form, are included within the documentation item called the NLSY High School Transcript Survey: Overview and Documentation. 

Transcript Surveys (1980-1983)

Transcript information on up to 64 courses was collected from high school records for civilian NLSY79 respondents who were expected to complete high school within the United States. A copy of the instrument used to collect transcript information, called the "Transcript Coding Sheet," is included within the NLSY High School Transcript Survey: Overview and Documentation (see School & Transcript Surveys Documentation in the NLSY79 Codebook Supplement).

ASVAB

The Armed Services Vocational Aptitude Battery (ASVAB) was administered to most NLSY79 respondents in 1980 as part of a Department of Defense effort to renorm this military enlistment test. The scores from this supplemental data collection are included in the NLSY79 data file. For details, see the Aptitude, Achievement & Intelligence Scores section.

Interviewer's Reference Manual (Question-by-Question [Q by Q] specifications)

Each questionnaire or set of survey instruments is accompanied by an Interviewer's Reference Manual. This document provides NORC interviewers with background information on the NLSY79 and detailed question-by-question instructions for administering and coding the questionnaire, Employer Supplement, Household Interview Forms, and other survey supplements. Separate Q by Q's exist for each survey year. Printed copies of the CAPI help screen information, which each interviewer could access during the course of the interview, replace the traditional interviewer's manual instrument beginning with the 1993 release.