Events at CERGE-EI

Katarína Borovičková, Ph.D.

New York University, USA

________________________________________

Authors: Katarina Borovickova, Fernando Alvarez and Robert Shimer

Abstract: We consider a discrete time mixed proportional hazard (MPH) model of duration. We prove that the baseline hazard and the frailty distribution of unobserved heterogeneity are nonparametrically identied using multiple-spell data, and use this to develop a GMM estimator of the baseline hazard. Our approach imposes no restrictions on the shape of the baseline hazard or the unobserved frailty distribution, allows for competing risks and spell-specic observable characteristics, and applies to right-censored data. The GMM specication is linear in the baseline hazard, which makes estimation and inference straightforward. We also develop tests of whether the MPH model is the data generating process. We apply our estimation procedure to the duration of price spells in weekly store data from IRI. Our setup allows us to integrate lters for sale prices into our statistical model. In contrast to most of the existing literature, we nd substantial unobserved heterogeneity, accounting for a large fraction of the decrease in the Kaplan-Meier hazard over time. The baseline hazard of regular price changes is mostly at except for anotable spike near one year duration.

________________________________________
Full Text: Consistent Evidence on Duration Dependence in Price Changes