Sharpness in randomly censored linear models

This work proves that inferences on parameter vectors based on moment inequalities typically used in linear models with outcome censoring are sharp, i.e., they exhaust all the information in the data and the model. This holds for fixed and randomly censored linear models under median independence where the censoring can be endogenous.

MoreLess

Year of publication:	2011
Authors:	Khan, Shakeeb ; Ponomareva, Maria ; Tamer, Elie
Published in:	Economics Letters. - Elsevier, ISSN 0165-1765. - Vol. 113.2011, 1, p. 23-25
Publisher:	Elsevier
Keywords:	Censored models Sharp set Identification Conditional moment inequalities

More details

Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10009275170