Book Chapter

Hazard smoothing along two time scales

Carollo, A., Putter, H., Eilers, P. H. C., Gampe, J.
In: Irigoien, I., Lee, D., Martínez-Minaya, J., Rodríguez-Álvarez, M. X. (Eds.): Proceedings of the 35th International Workshop on Statistical Modelling: July 20-24, 2020, Bilbao, Basque Country, Spain, 31–34
Bilbao, Servicio Editorial de la Universidad del País Vasco / Euskal Herriko Unibertsitateko Argitalpen Zerbitzua (2020)
Open Access

Abstract

The occurrence of events is mostly modelled by the hazard, and usually one considers only one preferred time scale. Other time scale(s) that may influence the event of interest are incorporated as a (time-varying) covariate(s).
Here we propose an approach to estimate the hazard as a smooth bivariate function over two time scales using P -splines. We illustrate the model by analyzing the transition from cohabitation to marriage where the age of the individual and the duration of the cohabitation are relevant. Data come from the German Family Panel (pairfam) and we demonstrate that considering the two time scales jointly provides additional insights about the transition from cohabitation to marriage.

The Max Planck Institute for Demographic Research (MPIDR) in Rostock is one of the leading demographic research centers in the world. It's part of the Max Planck Society, the internationally renowned German research society.