Temporary and permanent unit non-response in follow-up interviews of the Health and Retirement Study

2011 Longitudinal and life course studies  
We study the effects of attrition and other unit non-response in the HRS on inferences about the distribution of socio-economic variables. A feature of the HRS is that efforts are made to bring non-respondents in a particular wave back in the next wave. We find that bringing back these temporary non-respondents substantially reduces the selection effects due to unit non-response. This applies to cross-section analyses but the same conclusion is obtained from our analysis of examples of panel
more » ... xamples of panel data models, explaining changes in wealth, health, or labour force participation. This conclusion has important implications for users and designers of the HRS and other longitudinal socio-economic surveys with a similar design. JEL codes: C33, C81, C44
doi:10.14301/llcs.v2i2.114 fatcat:4xvyxhhwendrlb6r7ifvzuzkny