Measurement error and data collection methods: effects on estimates from event history data

Event history data from panel surveys typically display a concentration of transitions at the seam between waves of data collection. This ‘seam effect’ is likely to bias estimated durations of benefit receipt, attenuate the estimated effects of explanatory factors on conditional exit probabilities and bias estimated duration dependence. This paper uses benefit histories from survey reports and matched administrative records to assess the extent of bias in key estimates. The paper also evaluates the effectiveness at reducing bias of dependent interviewing techniques, where information collected in a previous interview is used to remind the respondent of sources reported previously, or to verify that sources no longer reported have truly ended.