Special Supplementary Data Files
In addition to the four 2-year public-use data files that contain data from the main NSFG interviews with respondents, there are additional NSFG restricted-use data files available that supplement the respondent data collection for the periods 2011-2015 and 2015-2019. These supplementary files are based on Interviewer Observations data and paradata (data about the data collection process). Below is information on the content and uses of these supplementary data.
The Interviewer Observations and Paradata files and additional documentation are available through the NCHS Research Data Center (RDC). For further information about these data, contact NSFG staff at nsfg@cdc.gov.
For information about how to access and use these data, please visit the RDC website or email rdca@cdc.gov.
Interviewer Observations Data Files
The Interviewer Observations data files are restricted-use files that contain responses from the interviewers who conducted interviews that took place in 2011-2015 and 2015-2019. Interviewers filled out a paper questionnaire or, for a small proportion of cases, entered responses on a smartphone (2011-2015 only), at the end of the survey while the respondents were completing the ACASI portion of the interview on the NSFG laptop.
All NSFG respondents (male and female) interviewed in 2011-2013 or 2013-2015 are included in the 2011-2015 interviewer observations data file, and all respondents interviewed in 2015-2017 or 2017-2019 are included in the 2015-2019 data file. The data files contain responses from the interviewers for most respondents, and where observation data were not provided, the variables will show “not ascertained” codes.
Documentation includes a file index listing all variables with short descriptions, a User’s Guide, a codebook with details and frequencies for each variable, and the paper questionnaire. The Interviewer Observations data files are intended to be used in conjunction with NSFG respondent-level (or female pregnancy level) data files. The Interviewer Observations data files contain a case ID that is the same as the case ID on the female and male main data files. This CASEID variable should be used for merging interviewer observations and respondent data files as needed for analysis. The Interviewer Observations data files also contain quarter of interview and a variable for sex of the respondent, allowing differentiation by data release and by male/female, within each four-year file. Weights for both two-year files and for the respective four-year combined files are available. Thus, different datasets can be created through merging, for various analytic purposes.
- 2011-2015 File Index [PDF – 104 KB]
- 2011-2015 User’s Guide [PDF – 26 KB]
- 2011-2015 Form [PDF – 63 KB]
- 2015-2019 File Index – 508 [PDF – 467 KB]
- 2015-2019 User’s Guide – 508 [PDF – 41 KB]
- 2015-2019 Form -508 [PDF – 102 KB]
Paradata Files
The 2011-2015 and 2015-2019 Paradata files are restricted-use files that include data describing the NSFG data collection process, for fieldwork spanning each of these 4-year periods:
- September 2011 to September 2015, corresponding to the NSFG file releases for 2011-2013 and 2013-2015
- September 2015 to September 2019, corresponding to the NSFG file releases for 2015-2017 and 2017-2019
The Paradata files include information for these two periods on all housing units that were randomly sampled for the NSFG. The files include records for each sample housing unit that responded to a screener and/or had an age-eligible respondent who completed a main NSFG interview, as well as housing units that ultimately did not respond to either the screener or the main interview. The Paradata files do not contain any data from the main respondent interviews. Types and sources of data included on these Paradata files are described in the Paradata User’s Guide and all variables on the files are listed in the File Index. These data can be used to assess potential non-response bias as well as other methodological questions of interest. The Paradata files are intended for use as both stand-alone data files and as files that can be linked with the NSFG public-use data files and restricted files using the case ID (CASEID variable) that is common to all files.