Are data from the CPS “reinterview surveys” available anywhere in IPUMS? As I understand it, the Census Bureau conducts follow-up interviews with survey respondents on a quarterly (?) basis in order to verify their labor force status. Several respondents mis-report their labor force status in the initial interview, which is subsequently corrected in the follow up surveys.
Is this information already incorporated in the EMPSTAT variable? May it be found in the flag for this variable QEMPSTAT?
Previous studies (e.g. Abowd and Zellner, 1985) have shown that this misclassification error can be quite substantial and affects the analysis of gross flows data.
The current CPS technical paper has a chapter (4-2) on the reinterview process, including tables with reinterview statistics. The reinterview file is not released in the Public Use Microdata Sample (PUMS) file that we harmonize and likely can only be obtained through an RDC request. Reinterviews are a quality check for census field representatives (FRs); there is no mention in the technical paper that the reinterview leads to data being edited. I was also not able to find variables regarding reinterviews in the PUMS data dictionary. I suspect therefore that the results of the reinterviews are not incorporated in the data released by Census for EMPSTAT or QEMPSTAT; edits to EMPSTAT that are flagged by QEMPSTAT are usually allocations for cases with missing data (see the PUMS documentation for more information about allocation flags).
This is great, thank you very much Ivan.
But isn’t it also possible that Census does incorporate the results of the reinterviews, and then only releases edited responses in the PUMS? If they are already incorporated, this would also explain why there is no mention of reinterview variables in the data dictionary. I really appreciate you pointing me to the technical paper. I will also take a look at Chapter 4-2 so that I am on the same page (no pun intended).
Relatedly, I was wondering if you could help me understand QEMPSTAT a bit better. Is this a variable coded specifically by IPUMS, or is there a direct mapping to a Census PUMS variable? My understanding of allocation flags in the Census PUMS data is that they tell you how the responses were allocated (logical, hot deck, cold deck, etc.), but the QEMSTAT codes read differently.
Thanks again for your help!
It is possible that Census ultimately does incorporate the results of the reinterviews into the PUMS data, but since there is no mention of this either in the chapter or in the PUMS documentation, I can only speculate on this account. I recommend reaching out to Census directly at email@example.com to confirm whether the reinterview data is or isn’t incorporated into the PUMS.
Census provides reallocation flags for a number of variables in the file; data for QEMPSTAT comes from the reallocation flag for labor force status, PXMLR. While Census uses a variety of methods to impute data such as logical and hot deck imputation, the method is not reported for the majority of allocation flags, but only for certain health insurance and disability variables asked in the ASEC (see for example HEALTH and its data quality flag QHEALTH). Code labels for BMS variable flags are provided in non-ASEC codebooks (see page 196 in this October 2021 codebook) and report the type of change rather than the imputation method used.
Perfect, thanks for your help Ivan! This is exactly the info I was looking for. I will try and talk to Census directly to dig deeper into the reinterview data.