Using Latent Variable Modeling for Discrete Time Survival Analysis: Examining the Links of Depression to Mortality

Abstract

Using a latent variable modeling approach to discrete time survival analysis, the dynamics of the relationships of depression and body mass index to mortality are examined with data from the multiwave, nationally representative Health and Retirement Study. A set of medical and demographic variables are employed as time-invariant covariates along with lag-1 depression scores and body mass indexes as time-varying covariates for mortality within an up to 2-year follow-up interval. The results indicate marked links of immediately prior depression levels, as well as notable relations of the body mass indexes, to within-wave mortality in middle-aged and older adults. The approach highlights the benefits of using latent variable modeling for survival analysis, and its findings represent potentially important relationships of clinical and theoretical relevance.

Keywords:

• body mass index
• depression
• discrete time survival analysis
• latent variable modeling
• mortality
• time-invariant covariate
• time-varying covariate

Notes

¹ The depression measure employed in this article is the overall score resulting from a short form of the widely used Center for Epidemiologic Studies Depression scale (CES–D; Radloff, 1977; cf. Raykov, Gorelick, et al., 2017a, 2017b). The CES–D measure used here included eight indicators of a respondent’s feelings during the week prior to the interview. Six negative indicators measure whether the respondent experienced feeling depressed, like everything is an effort, sleep is restless, felt alone, felt sad, and could not get going. The remaining two positive indicators (reverse-coded) include having felt happy and enjoyed life. At Wave 1, the response categories for all items were all or almost all of the time, most of the time, some of the time, or none or almost none of the time. At all following waves, the same eight indicators were assessed but the questions were phrased in terms of how the respondents felt “much of the time” over the week prior to the interview and the response categories were dichotomous: yes–no. The CES–D scale has high internal consistency, acceptable test–retest reliability, and excellent concurrent validity with clinical and self-report criteria across population subgroups and thus is a useful tool for population studies of depression (Radloff, 1977). Acceptable validity and reliability have also been shown for the short forms of the CES–D scale such as those used by the HRS (Andersen, Malmgren, Carter, & Patrick, 1994; Levine, 2013).