Variable selection in discrete survival models including heterogeneity

Groll, Andreas and Tutz, Gerhard (2017): Variable selection in discrete survival models including heterogeneity. In: Lifetime Data Analysis, Vol. 23, No. 2: pp. 305-338

Abstract

Several variable selection procedures are available for continuous time-toevent data. However, if time is measured in a discrete way and therefore many ties occur models for continuous time are inadequate. We propose penalized likelihood methods that perform efficient variable selection in discrete survival modeling with explicit modeling of the heterogeneity in the population. The method is based on a combination of ridge and lasso type penalties that are tailored to the case of discrete survival. The performance is studied in simulation studies and an application to the birth of the first child.

• Item Type: Journal article
• Faculties: Mathematics, Computer Science and Statistics > Statistics
• Subjects: 500 Science > 510 Mathematics
• ISSN: 1380-7870
• Language: English