Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/63159 
Year of Publication: 
2000
Series/Report no.: 
Memorandum No. 2000,20
Publisher: 
University of Oslo, Department of Economics, Oslo
Abstract: 
Known results on the identification of structural duration dependence in the presence of unobserved heterogeneity depend crucially on the proportional hazards assumption. Here, I show that variation in covariates over time, combined with variation across observations, is sufficient to ensure identification without the proportional hazards assumption. The required variation over time is minimal.
JEL: 
C41
Document Type: 
Working Paper

Files in This Item:
File
Size
196.53 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.