TY - JOUR
AU - Singer,, B.
AB - Abstract This paper presents new identifiability conditions for the Cox proportional hazard model for duration data when unobserved person specific variables are present. We compare our conditions with those presented by Elbers and Ridder. We also present identifiability conditions for a rich class of parametric hazard models without regressor variables. This content is only available as a PDF. Author notes This research was supported by NSF Grant SES-8109763 and NIH Grant NIH-1-R01-HD16846-01. Versions of this paper were presented at seminars at Johns Hopkins, MIT, Wisconsin, UCLA, Princeton, and the University of Western Ontario. We thank Grayham Mizon, Kevin M. Murphy, George Yates and two referees for helpful comments. © 1984 The Society for Economic Analysis Limited
TI - The Identifiability of the Proportional Hazard Model
JF - The Review of Economic Studies
DO - 10.2307/2297689
DA - 1984-04-01
UR - https://www.deepdyve.com/lp/oxford-university-press/the-identifiability-of-the-proportional-hazard-model-B60A631efD
SP - 231
VL - 51
IS - 2
DP - DeepDyve
ER -