Potential selection bias in FSSTMPDAY

1

Hello! I am currently working with CPS data to construct a panel dataset that identifies, for each month of a given year, whether an individual received food stamps (SNAP) and, if so, the specific day on which the benefits were received—using the FSSTMPDAY variable.

My goal is to build this panel by combining information from the Food Security Supplement and ASEC, covering the period 1995–2011, during which FSSTMPDAY was collected.

I would greatly appreciate if you could (a) provide some guidance on the most appropriate methodology for this task and (b) clarify a few points regarding the collection and interpretation of FSSTMPDAY:

  1. Post-2001 FSSTMPDAY Universe
    FSSTMPDAY is non-missing in the data only for individuals who answered “yes” to FSSTMPNOV and “no” to FSSTMPDEC. Can you confirm that these are individuals who have not yet received their December benefits (i.e., still active recipients), as indicated in the description of FSSTMPDAY, and not individuals who exited the SNAP program in November (e.g., due to ineligibility or non-recertification) and those are not receiving benefits in December?

  2. 1995 and 1996 Universe Definition
    FSSTMPDAY is asked only of those who received benefits in the past 30 days and whose last benefit was in the interview month or the prior month. Is it correct to interpret this as follows: it is not the case that this question is asked only if someone iscurrently on SNAP. That is, someone who (hypothetically) received SNAP on March 17, 1995—and whose benefits ended that same month—would still be asked FSSTMPDAY if interviewed on, say, April 14, 1995?

  3. 1999–2001 Universe Filter
    FSSTMPDAY is only asked of households that received benefits in both the current and previous calendar month. Could you confirm if this understanding is correct: this information is available only for those who receive foodstamp for 2 months (consecutively), that is that of the interview and the one prior?

  4. 1997–1998 Universe: “Received in Past Year”
    FSSTMPDAY is asked of those who received SNAP in the past year and who last received benefits in the interview month or the two previous months. Could you clarify whether “past year” refers to the 12 months prior to the interview date (e.g., April 1996–April 1997 for an April 1997 interview), rather than the calendar year?

These questions are relevant as I am also trying to understand the potential selection bias introduced by the varying FSSTMPDAY collection rules across years. If you have any recommendations for best practices or references related to this issue—especially how to model or correct for this kind of selection—I would be very grateful.

Thank you very much for your time and assistance.

2

Let me answer your questions by going through the universe statements for FSSTMPDAY chronologically. To preface, all of the universe definitions for this variable are backwards-looking; they never restrict respondents based on current SNAP enrollment status or expectations for future benefits. I obtained these universe definitions by reviewing the corresponding Food Security Supplement codebook. The variable that reports the date that benefits were received is alternatively coded as either HESP2D (1998-onwards) or as HES9AD.

1995-1996:

  • Someone in the household must have received benefits within the past 30 days from the interview date, and
  • The household’s income must have been below 185% of the poverty threshold.

1997-1998:

  • Someone in the household must have received benefits during either the interview month or one of the two previous months, and
  • The household’s income must have been below 185% of the poverty threshold.

While from 1997-1998 there is also a requirement that someone is the household have received benefits with the 12 months prior to the interview date, this criteria is already captured by the requirement to have received benefits within the previous two months. Households that received benefits more than two months previous to the interview, even if it was less than 12 months, would not be in universe for this question.

1999-2001:

  • Someone in the household must have received benefits during either the interview month or one of the two previous months, and
  • The household’s income must have been below 185% of the poverty threshold, or
    • Someone in the household received WIC during the previous 30 days (in 2000).
    • Reported that the household in the past 12 months “ever ran short of money and tried to make food or food money go further” (in 2001).

In 1999-2001, there is no requirement to have received the benefits in both the current and previous calendar month (just one is sufficient).

2002-2011:

  • Someone in the household must have received benefits in November, and
  • Benefits were not (or not yet) received in December, and
  • The household’s income must have been below 185% of the poverty threshold, or
    • Reported that the household in the past 12 months “ever ran short of money and tried to make food or food money go further” .

In 2002-2011, this identifies households that either exited the SNAP program in November and did not receive (or do not expect to receive) benefits in December, or are currently enrolled and have not yet received their December benefits. The purpose of this question appears to be to gauge the number of days the household went without SNAP benefits, not to obtain the date that households typically receive SNAP benefits. As stated, there is no variable that identifies current enrollment in SNAP in the data.

Since benefits are typically received on the same day each month, you might be able to separate these two groups by observing the reported date of November benefits. Note that the CPS interview week typically falls on the week containing the 19th of each month. Households that received benefits in November are separated identified in FSSTMPNOV.