Attrition and misclassification of drop-outs in the analysis of unemployment duration

Carling et al (1996) analyze a large data set of unemployed workers in order to examine, inter alia, the effect of unemployment benefits on the escape rate to employment. In this paper we take a closer look at the 20 per cent of workers who were drop-outs and check the empirical justification for modeling attrition as independent right censoring in the analysis of unemployment duration. It may very well be that dropping out, i.e. attrition, often occurs due to employment. In the analysis, we refer to these individuals as misclassified in that they are typically treated as if their unemployment spell went beyond the time of attrition. We propose to follow up the drop-outs by a supplementary sample and apply a Multiple Imputation approach to incorporate the supplementary information. Our follow-up study revealed that 45% dropped out due to employment. The escape rate to employment was as a consequence underestimated by 20 per cent, implying that the effect of unemployment benefits on the escape rate is likely to be much greater than reported in Carling et al (1996).

KEY WORDS: Follow-up study; Informative censoring; Multiple imputation; Register data; Survival models.