Explaining differences in labour market transitions between panel and life-course data in West-Germany

Abstract

Panel and life-course data are ideally suited to unravelling labour market dynamics, but their designs differ, with potential consequences for the estimated relationships. To gauge the extent to which these two data designs produce dissimilar transition rates and the causation thereof, we use the German Life History Study and the German Socio-Economic Panel. Life-course data in particular suffer from recall effects due to memory bias causing understated transition probabilities. Panel data suffer from seam effects due to spurious transitions between statuses recalled in activity calendars that generate heaps at particular time points and cause overstated transition probabilities. We combine the two datasets and estimate multilevel (multistate) discrete-time models for event history data to model transitions between labour market states taking these factors into account. Though we find much lower transition rates in the life-course study, confirming the results of Solga (Qual Quant 35:291–309, 2001) in this Journal for East-Germany, part of the difference can be explained by short spells recall bias. The estimated models on exit, re-entry and job mobility on the combined datasets show indeed a negative retrospective design effect. Another specification that includes the length of the recall period shows no significant decrease in the transition probabilities with increasing length, suggesting that the negative design effect is due to other design differences.