Appendix 6: Event History Creation and Documentation

Appendix 6: Event History Creation and Documentation

Program Participation Event History Arrays

Program participation arrays are constructed individually for four programs--Unemployment Insurance, AFDC, Food Stamps, and WIC. These arrays were also constructed for Worker's Compensation for rounds 1 to 3. The AFDC array includes all federal and state programs created under Temporary Assistance to Needy Families (TANF) or any government program for needy families that replaces AFDC. All other programs (e.g., LIHEAP, SSI, other) are combined into one set of questions in the survey and are presented in a sixth array entitled 'Other.' For each program type, except Unemployment Insurance, three arrays are created. All program participation arrays provide information starting in the month that the respondent turned 14. The Unemployment Insurance arrays end in the month that the respondent was last interviewed, while the other arrays end by September 2009.

A secondary set of variables translates the reported beginning and ending dates (month and year) of a spell within the program into the continuous month scheme (e.g., AFDC_START_MONTH and AFDC_STOP_MONTH). More information about the continuous month scheme is provided in Appendix 7.

The main array, (e.g., AFDC_STATUS), presents the status--receiving or not--of a respondent during each month. When asked for the start or stop date of a spell, the respondent could answer 'don't know' or 'refuse' to any component. In this case, the respondent was then asked how many weeks the spell lasted. The number of reported weeks was then divided by 4.3 to determine the equivalent number of months. If a fraction of a month was reported, then the entire month was counted as a month receiving benefits. Using a combination of start date, stop date, and week information, each spell was defined and a value of '1' inserted into the status array to indicate months of receipt. The months that a respondent did not receive that benefit, but was eligible to receive it, have a value of '0.' An edit variable (e.g., AFDC_EDIT_DATE) flags respondent-reported and imputed dates. The process by which imputed dates and the corresponding edit flag were assigned is described below:

Flag Definition
Edit Flag=1: Respondent reported participation dates Respondent reported a complete start and stop date and is not currently receiving. If the respondent reports still receiving at the time of the interview, the interview date is assigned as the temporary stop date. In the next survey round, the respondent will be asked if he or she is still receiving; if not, a permanent stop date equivalent to the previous round's interview date will be assigned. If the respondent reports receiving, participation will continue in filling the array.
Edit Flag=2: Start month imputed Total weeks known: If the respondent reports not currently receiving, then set the month equal to January and count forward by the number of weeks to imply a stop date. If currently receiving, then count back by the number of weeks from the interview date to impute a start month. If the month indicated by the count falls short of the start year, the start month is December of the start year. If the month occurs in the year before the reported start year, then the start month is January of the start year.
Total weeks unknown: If the respondent reports not currently receiving, then the start month is set to January. Use December as the stop month and the start year as the stop year. If the respondent reports currently receiving, use December as the start month.
Edit Flag=3: Start month and year imputed Total weeks known: Count back by the number of weeks from the interview date if currently receiving. If not currently receiving, then count back from interview date to find the most recent year the respondent could have begun receiving and call the start date January of that year; then count forward the number of weeks from that date to imply a stop date.
Total weeks unknown: If currently receiving or the stop date is reported, begin the spell at the respondent's 14th birthday (in round 1) or the last interview month (in later rounds).
Edit Flag=4: Stop month imputed Total weeks known: If not currently receiving, then count forward from start date. If the month indicated falls short of the stop year, then use January of the stop year as the stop month; if the number of months exceeds the stop year, then set the stop month to December of the stop year. If the stop year is equal to the interview year and the stop month exceeds the interview month, then stop at the interview date.
Total weeks unknown: Use December of stop year or the interview month, whichever comes earlier, for the stop month.
Edit Flag=5: Stop month and year imputed Total weeks known: If not still receiving, count forward from the start date.
Total weeks unknown: If not currently receiving, then use December of the start year as the stop month and the start year as the stop year.
Edit Flag=6: Start and stop dates imputed Total weeks unknown: The imputed dates are based on the previous interview's date (start date) to the current interview date (stop date); in round 1, the last interview date is the respondent's 14th birth month and year.
Edit Flag=7: Start and stop dates complete but gap information missing No information was collected about gaps in receipt.

Starting in survey year 2009, we have added values 8, 9, 10, 11, 12, 13, and 14 to Edit Flag. Their definitions are similar to those of Edit Flag=1, 2, 3, 4, 5, 6, and 7, respectively, except the stop dates are truncated to September 2009.

If a respondent reports receiving in a particular month, a second array presents the amount received in each month (e.g., AFDC_AMT). The dollar values asked about during the interview were meant to be monthly values. However, some responses were higher than the federal or state limits on the amount received from a particular benefit. A likely reason is that the respondent mistakenly reported a total value rather than a monthly value. Values determined to be too high were divided by the number of months the respondent reported receiving the benefit. These values were used in the AMT arrays instead. A second set of edit variables (e.g., AFDC_EDIT_AMT) flags these values for a particular spell.

If a respondent reports receiving in a particular month, the persons in the household who benefit from the program in each month (e.g., respondent only, child only, respondent and child) are recorded in a third array (e.g., AFDC_HH). This program condenses the set of answers from the question in the survey that collects this information; for example, see YPRG-35920_UPD.01~000001 to YPRG-35920_UPD.01~000005 for AFDC. Users should note that this array is not present for Worker's Compensation and Unemployment Insurance because these programs are collected for the respondent only.

Other information
A few respondents report receiving assistance but then deny that receipt in a later interview. These situations are treated in the same way as in the marriage arrays, as described above. The denial flag variables for the program participation arrays incorporate the name of the program (e.g., AFDC_DENY).

Researchers should be aware of an important source of variability in the Worker's Compensation data. These data suggest that some respondents report the dates the payment was actually received and some report the period of time to which the payment applied. For example, if a respondent was out of work for six months but received a lump sum payment a year later, he or she might report either the date the lump sum was paid or the dates he or she was unable to work.