Click the icon to view and/or download the PDF file.
Once you are in the PDF file, use your browser back button to return to this page.
Abstract
In many surveys, information on respondents’ education histories is restricted to the level and sometimes the date they attained their highest degree. We compare estimates of education effects on first birth transitions using imputed histories based on this rudimentary information with estimates drawing on complete histories, using the German Life History Study. We find that imputed histories produce relatively reliable estimates for most but not all education categories, especially when information on the date the highest degree was attained is available. We investigate possible explanations for these findings and indicate contexts in which biases may be stronger.
Author's affiliation Cordula Zabel Institute for Employment Research (IAB), Nuremberg, Germany
