This paper shows that popular linear fixed-effects panel-data estimators (first-differences, within-transformation) are biased and inconsistent when applied in a discrete-time hazard setting, that is, one with the outcome variable being a binary dummy indicating an absorbing state, even if the...

Since the early 1980s, the econometric analysis of duration variables has become widespread. This chapter provides an overview of duration analysis, with an emphasis on the specification and identification of duration models, and with special attention to models for multiple durations. Most of...

This paper defines economic slumps as sequences of structural breaks exhibiting a specific pattern. We identify 58 such episodes between 1950 and 2008 among 138 countries, and then examine the phases of decline and their duration. In some countries declines last extremely long, and we put...

We investigate the role of industry and region-specific conditions for the survival of new businesses in innovative and in other manufacturing industries. The data comprises all German manufacturing start-ups of the 1992 to 2005 period. In contrast to studies for some other countries, we find...

In 2005, the unemployment compensation for long-term unemployed was reduced in Germany. We examine how this reform affected the transition probability to employment. Additionally, we inspect how this effect varies over unemployment duration. We estimate proportional hazard models using German...