urban institute nonprofit social and economic policy research

National Survey of America's Families

1997 Methodology Series

Dean Brick, P., Kenney, G., McCullough-Harlin, R., Rajan, S., Scheuren, F., Wang, K., Brick, J.M., and Cunningham, P., No. 1: National Survey of America's Families: Survey Methods and Data Reliability, July 1999.

This is a new release. The original Survey Methods and Data Reliability was initially prepared to accompany the January 25, 1999 release of the Snapshots of America's Families. Since its release on January 25, 1999, 11 more detailed methodology reports have been created. This new version of Survey Methods and Data Reliability Report No. 1 includes a revised and more in-depth introduction to the National Survey of America's Families, its sample design and data collection techniques, and estimation methods.

An overview is provided of how both households with and without telephones were sampled, the format of interviews, and types of questions asked. In addition, the methods used to minimize errors and compensate for those that are unavoidable in data collection are described. Finally, the report presents information on the survey's resulting reliability—both in terms of sampling and nonsampling errors.

Judkins, D., Shapiro, G., Brick, J.M., Flores-Cervantes, I., Ferraro, D., Strickler, T., and Waksberg, J., No. 2: 1997 NSAF Sample Design Report, March 1999.

Report No. 2 provides a detailed description of the 1997 NSAF sample design for both telephone and in-person interviews. Particular emphasis is given to the difficulties that arose because of the dual-frame nature of the survey. In addition, methods used to subsample low-income families are described, as are techniques used to sample children and adults within households.

Brick, J.M., Shapiro, G., Flores-Cervantes, I., Ferraro, D., and Strickler, T., No. 3: 1997 NSAF Snapshot Survey Weights, March 1999.

Report No. 3 focuses on the methods employed to produce estimation weights and the procedures to use these weights to make state and national estimates from the survey data. These weights were used to produce estimates in Snapshots of America's Families, the first reports released from the NSAF. In addition, the coverage achieved in the 1997 NSAF is also compared to the coverage in other surveys.

Flores-Cervantes, I., Brick, J.M., and DiGaetano, R., No. 4: 1997 NSAF Variance Estimation, March 1999.

Report No. 4 describes the methods and results of computing sampling errors for the 1997 National Survey of America's Families (NSAF). First, an overview of the sample design and summaries of the precision of the survey estimates for both estimates of children and adults are presented. The second chapter presents a general review of the two main methods of computing sampling errors or variances of estimates from surveys with complex survey designs like the NSAF. The third chapter discusses why the replication method of variance estimation was chosen as the main method for the NSAF and describes procedures for computing replicate estimates of variance from the data. The fourth chapter describes how software available for computing sampling errors can be used with the data. The final chapter summarizes the findings and methods used.

Cunningham, P., Shapiro, G., and Brick, J.M., No. 5: 1997 NSAF In-Person Survey Methods, March 1999.

Report No. 5 describes processes used to complete the in-person component of the NSAF. The in-person component was designed to augment the telephone survey with a sample of households without telephones. The report outlines the pilot study, procedures and materials used to conduct the interviews, the component's management structure, field organization, recruiting, and training, response rates, and special issues/problems that arose in the field during data collection.

Ehrle, J., and Moore, K., No. 6: Benchmarking Child and Family Well-Being Measures in the NSAF, March 1999.

Report No. 6 assesses several measures of child and family well-being used in the National Survey of America's Families (NSAF): parent mental health, child school engagement, behavioral and emotional problems in children, parent aggravation, reading to children, taking children on outings, and child participation in sports, clubs, and lessons. Each measure is considered in terms of its relevance to research on welfare reform, its psychometric properties (including quality of the data, internal reliability, and construct validity), and how estimates using the measure compare with data from other large samples using the same or similar measures.

Groves, R., and Wissoker, D., No. 7: Early Nonresponse Studies of the 1997 National Survey of America's Families, March 1999.

Report No. 7 describes studies that were conducted to attempt to gain some insight into the characteristics of nonrespondents to the 1997 NSAF, and to assess the impacts of missing data from unit nonresponse on NSAF statistics. These studies included a) comparison of key NSAF statistics to similar measures computed from the Current Population Survey; b) comparison of NSAF results among respondents requiring different levels of effort to obtain an interview; c) comparison of NSAF respondents with respondents to a second phase survey of NSAF nonrespondents; and d) alternative statistical models producing overall population estimates incorporating different assumptions about nonresponse.

A key finding of these studies was that there are very few estimates of nonresponse error in the NSAF that exceed magnitudes expected from sampling variability alone.

Brick, J.M., Flores-Cervantes, I., and Cantor, D., No. 8: 1997 NSAF Response Rates and Methods Evaluation, March 1999.

Report No. 8 provides information on the response rates obtained for the 1997 NSAF (taking the estimation weights into account) and explains the methods used to compute these rates. Tables are included of response rates for important subgroups, such as telephone and nontelephone households. The report reviews approaches used to increase the response rates, and concludes that the response rates for the 1997 NSAF were higher than those typical of this type of survey.

Vaden-Kiernan, N., Cunningham, P., Dipko, S., Molloy, K., and Warren, P., No. 9: 1997 NSAF Telephone Survey Methods, April 1999.

Report No. 9 describes methods employed to complete the telephone component of the 1997 NSAF including a list-assisted method to select the random digit dialing (RDD) sample of telephone numbers and computer-assisted telephone interviewing (CATI) for screening and interviewing. Subsampling of telephone households is described, as is how respondents were selected, information on the topics covered during the interview, and data quality control methods used.

The report concludes that there were few difficulties with the telephone interviewing component of the NSAF. Those that did exist, primarily related to within household coverage issues and family definition problems.

Dipko, S., Skinner, M., Vaden-Kiernan, N., Coder, J., Rajan, S., and Scheuren, F., No. 10: 1997 NSAF Data Editing and Imputation, April 1999.

Report No. 10 focuses on data editing techniques, including data processing, how data errors were dealt with, how edits were made, coding guidelines, as well as how data were "filled in" when values were missing. Some discussion is also provided of the relative size of sampling variance to mean square error.

Russell, B., Leonard, M., and Scheuren, F., No. 11: 1997 NSAF Child Public Use File Codebook, March 1999.

Report No. 11 provides documentation for the Child Public Use File, which includes data on 33,703 sampled children under 18 years of age from the 1997 NSAF. Also included on the file is some limited related information on the adults who care for them and the family settings in which they live.

If you are currently using this initial release of the 1997 NSAF Child Public Use File data, we recommend that you download and use our latest release, 1997 NSAF Child Public Use File Documentation and Codebook with Undercount-Adjusted Weights, Methodology Report No. 18. Should you need a copy of the initial child file, please contact nsaf@ui.urban.org or call 202-261-5377.

Wang, K., Dipko, S., and Vaden-Kiernan, N., No. 12: 1997 NSAF Questionnaire, October, 1999.

Report No. 12 focuses on the 1997 NSAF questionnaire. The introductory chapter describes the household screener, household verification and extended interview. In addition, the chapter covers respondent selection, types of NSAF interviews and the NSAF family definition so that the reader may gain a better understanding of the NSAF questionnaire. The remainder of the report provides the full text of the questionnaire.

Russell, B., Converse, N.,and Scheuren, F., No. 13: The 1997 NSAF MKA Public Use File Documentation and Codebook, July 1999.

Report No. 13 provides documentation for the Most Knowledgeable Adult (MKA) Public Use File, which includes data on 27,599 sampled adults most knowledgeable about each sample child from the 1997 NSAF.

Contained here is an overview of the MKA File, including how to access and download it. Detailed information on each variable is then presented, including where it comes from on the NSAF questionnaire, how it was created, what records are missing or inapplicable entries, and (usually) why. Weighted and unweighted distributions and the question wording for each variable are also included. Two cross-reference lists are provided to assist the reader in locating variables.

If you are currently using this initial release of the 1997 NSAF MKA Public Use File data, we recommend that you download and use our latest release, 1997 NSAF MKA Public Use File Documentation and Codebook with Undercount-Adjusted Weights, Methodology Report No. 19. Should you need a copy of the initial MKA file, please contact nsaf@ui.urban.org or call 202-261-5377.

Scheuren, F., Schmidt, S., Capizzano, J., Barsimantov, J., Matani, S., Brick, J.M., Flores-Cervantes, I.,Hankins, T., Vandivere, S., No. 14: 1997 NSAF Impact of Census Undercount-Adjusted Weights on Survey Estimates,October 2000.

This report completes the methodological discussion of 1997 NSAF estimation that was begun in report no. 3 in this series. Here our main goal is to describe how we brought the 1997 NSAF up to census undercount-adjusted control totals and what difference this made. In report no. 3, we described the first estimation approaches used for the 1997 survey. (report no. 3 also explains how we brought the survey up to census-level controls.)

The use of census-undercount controls allows researchers to more readily compare NSAF results with those of most other large national surveys, like the Current Population Survey (CPS) or the National Health Interview Survey (NHIS). As will be seen, this reestimation effort also allowed us to refine some other steps taken earlier.

Scheuren, F., Wang, K., Kenney, G., et al No. 16: 1997 NSAF Technical Papers, March 2000.

Report Number 16 is a collection of occasional papers given at professional meetings and workshops on technical issues in the design of, implementation of, and results from the 1997 round of the NSAF.

Wigton, A., Scheuren, F., Wenck, S., Fan, J., Parker, A., and Smith, W., No. 17: 1997 NSAF Non-MKA (Other Adult) Public Use File Documentation and Codebook, January 2000.

Report No. 17 provides documentation for the Non-MKA (Other Adult) Public Use File, which includes data on 47,052 sampled adults (other than the MKAs, who are the most knowledgeable adults for each sample child) from the 1997 NSAF.

Contained here is an overview of the Non-MKA File, including how to access and download it. Detailed information on each variable is then presented, including where it comes from on the NSAF questionnaire, how it was created, what records are missing or inapplicable entries, and (usually) why. Weighted and unweighted distributions and the question wording for each variable are also included. Two cross-reference lists are provided to assist the reader in locating variables.

If you are currently using this initial release of the 1997 NSAF Non-MKA Public Use File data, we recommend that you download and use our latest release, 1997 NSAF Non-MKA Public Use File Documentation and Codebook with Undercount-Adjusted Weights, Methodology Report No. 20. Should you need a copy of the initial Non-MKA file, please contact nsaf@ui.urban.org or call 202-261-5377.

Wigton, A., Scheuren, F., Wenck, S., Zhang, H., Nooter, D., and Smith, W. No. 18: 1997 NSAF Child Public Use File Documentation and Codebook with Undercount Adjusted Weights, March 2000.

Report No. 18 provides documentation for the final Child Public Use File with Undercount-Adjusted Weights, which includes data on all 34,439 sampled children under 18 years of age from the 1997 NSAF. In an earlier public use file, documented in Report No. 11, a more limited data set was released that contains a subset of the variables provided here.

Contained here is an overview of the Child File, including how to access and download it. Detailed information on each variable is then presented, including where it comes from on NSAF questionnaire, how it was created, what records have missing or inapplicable entries, and (usually) why those entries are missing. Weighted and unweighted distributions and the question wording for each variable are also included. Two cross-reference listings are provided to assist the reader in locating variables.

The Child Public Use File with Undercount-Adjusted Weights is a compressed ASCII file contained in a self-extracting program that must be downloaded and unzipped. Users of the original NSAF Child Public Use File, released in the spring of 1999, or of the MKA Public Use File, released in the summer of 1999, will find the structure of this file very familiar. In addition, this methodology report is very similar in form to Methodology Report No. 11, the 1997 NSAF Child Public Use File Documentation and Codebook.

McCullough-Harlin, R., Russell, B., Safir, A., Scheuren, F., Wigton, A., Zhang, H., Nooter, D., Cohen, E., and Smith, W., No. 19: 1997 NSAF MKA Public Use File Documentation and Codebook with Undercount Adjusted Weights, June 2000.

Report No. 19 provides documentation for the complete Most Knowledgeable Adult (MKA) Public Use File with Undercount-Adjusted Weights, which includes data on 28,163 sampled adults most knowledgeable about each sample child from the 1997 NSAF. In an earlier public use file, documented in Report No. 13, a more limited data set was released that contains a subset of the variables provided here.

Contained here is an overview of the MKA File, including how to access and download it. Detailed information on each variable is then presented, including where it comes from on the NSAF questionnaire, how it was created, what records are missing or inapplicable entries, and (usually) why. Weighted and unweighted distributions and the question wording for each variable are also included. Two cross-reference lists are provided to assist the reader in locating variables.

The MKA Public Use File with Undercount-Adjusted Weights is a compressed ASCII file contained in a self-extraction program that must be downloaded and unzipped. Users of the earlier NSAF MKA Public Use File, released in July 1999, will find the structure of this file very familiar. In addition, this methodology report is very similar in form to Methodology Report Number 13, the NSAF MKA Public Use File Codebook.

McCullough-Harlin, R., Russell, B., Safir, A., Scheuren, F., Wigton, A., Zhang, H., Nooter, D., Walter, E., and Smith, W., No. 20: 1997 NSAF Non-MKA (Other Adult) Public Use File Documentation and Codebook with Undercount Adjusted Weights, June 2000.

Report No. 20 provides documentation for the complete Non-MKA (Other Adult) Public Use File with Undercount-Adjusted Weights, which includes data on 47,362 sampled adults (other than the MKAs, who are the most knowledgeable adults for each sample child) from the 1997 NSAF. In an earlier public use file, documented in Report No. 17, a more limited data set was released that contains a subset of the variables provided here.

Contained here is an overview of the Non-MKA File, including how to access and download it. Detailed information on each variable is then presented, including where it comes from on the NSAF questionnaire, how it was created, what records are missing or inapplicable entries, and (usually) why. Weighted and unweighted distributions and the question wording for each variable are also included. Two cross-reference lists are provided to assist the reader in locating variables.

The Non-MKA Public Use File with Undercount-Adjusted Weights is a compressed ASCII file contained in a self-extraction program that must be downloaded and unzipped. Users of the early NSAF Non-MKA Public Use File, released in January 1999, will find the structure of this file very familiar. In addition, this methodology report is very similar in form to Methodology Report Number 17, the NSAF Non-MKA Public Use File Codebook.

Converse, N., McCullough-Harlin, R., Safir, A., Scheuren, F., Yang, J., Nooter, D., Zhang, H., No. 21: 1997 NSAF Social Family Public Use File Documentation and Codebook with Undercount Adjusted Weights, November 2000.

Report No. 21 provides documentation for the Social Family Public Use File with Undercount-Adjusted Weights, which includes data on 44,781 sampled families from the 1997 NSAF.

This report includes an overview of the NSAF social family file, detailed information on each variable is then presented, including its location on the NSAF questionnaire, how it was created, and which records have missing or inapplicable entries and (usually) why. Weighted and unweighted distributions and the question wording for each variable are also included. Two cross-reference listings are provided to assist the reader in locating variables.

The Social Family Public Use File is a compressed ASCII file contained in a self-extracting program that must be downloaded and unzipped. Users of the earlier NSAF Public Use Files will find the structure of this file very familiar.

Converse, N., McCullough-Harlin, R., Safir, A., Scheuren, F., Yang, J., Nooter, D., Zhang, H., No. 22: 1997 NSAF CPS Family Public Use File Documentation and Codebook with Undercount Adjusted Weights, November 2000.

Report No. 22 provides documentation for the CPS Family Public Use File with Undercount-Adjusted Weights, which includes data on 47,171 sampled families from the 1997 NSAF.

This report includes an overview of the NSAF social family file, detailed information on each variable is then presented, including its location on the NSAF questionnaire, how it was created, and which records have missing or inapplicable entries and (usually) why. Weighted and unweighted distributions and the question wording for each variable are also included. Two cross-reference listings are provided to assist the reader in locating variables.

The CPS Family Public Use File is a compressed ASCII file contained in a self-extracting program that must be downloaded and unzipped. Users of the earlier NSAF Public Use Files will find the structure of this file very familiar.