Much of the value of the HRS as a study of aging is in its use of a number of innovative survey research techniques, including the use of proxy interviews. Researchers who include respondents with interviews by proxy in their analytic sample should be well informed about what a proxy interview is and how these respondents differ from the rest of the sample.
One of the main challenges in a survey of health and aging is that sample members who are in poor health may not be able to complete an interview*. Having missing data on the least healthy in the population results in a selectively healthy sample and limits our ability to draw conclusions about aging processes and the older U.S. population. Ideally, we would have data on every sample member, regardless of their ability to complete the interview.
HRS interviewers attempt to obtain interviews with all surviving sample members, but for those respondents who cannot complete an interview due to physical or cognitive limitations interviewers are instructed to complete the interview with someone who has sufficient knowledge about the respondent’s health, social, and economic situation to provide accurate data.
The following excerpt from the user document “Sample Evolution: 1992-1998” describes how a proxy interview is conducted (Section 6.B; pages 11-12):
When a proxy was needed for any of the reasons just described, the interviewers were instructed to attempt to interview the person who was most familiar with the financial, health, and family situation of the sampled individual. In practice, this was generally the spouse of the person if he or she was married or living with a partner. In the absence of a spouse, the proxy was often a daughter or a son, or less frequently another relative or a care giver. The relationship of the proxy to the sample person is noted in a variable that is present for each wave. In addition, if there was a proxy informant at two successive waves, there is a variable that indicates whether or not this was the same individual on each occasion.
A version of the questionnaire was developed that would be appropriate to administer to proxy informants. For most questions, this involved only wording changes (e.g., from “you” to “him” or “her”), but some questions were thought to be inappropriate to ask of proxies and so were omitted entirely. These included questions intended to assess psychological depression; the test of cognitive status; expectation questions; and questions about subjective evaluations of the person’s job or retirement. Proxy informants were asked a different set of questions designed to measure the cognitive abilities of the sampled person.
Respondents who have proxy interviews differ significantly from other respondents on physical and cognitive functioning, though they represent a relatively small portion of the sample. The number of interviews (of living, age-eligible sample members) completed by proxies varies from wave to wave, but it’s been around 4-5% in recent years. (Proxies also complete the exit and post-exit interviews so the number of proxies completing any interview is higher.) Still because proxies don’t answer all questions (e.g., depression symptoms, cognitive tests) you may be dropping 5% of your sample right off the bat, and these folks are not missing at random.
The key to working with the HRS data is knowing when proxies are and are not in your sample and the potential implications of including/excluding proxies for the conclusions you draw from your analyses. Fortunately it’s easy to identify proxy respondents using the *proxy variables available for each wave from the HRS core data (Tracker file) or the RAND file.
*Some respondents have a proxy interview because they could not take the interview in English or Spanish, because they were unwilling to be interviewed themselves but consented to having someone else complete the interview for them, or because there were concerns about the respondent’s ability to answer questions accurately.