|
Activity Number:
|
444
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
ENAR
|
| Abstract - #307796 |
|
Title:
|
Inference in Randomly Censored Regression Models Using Conditional Moment Inequalities
|
|
Author(s):
|
Shakeeb Khan*+
|
|
Companies:
|
Duke University
|
|
Address:
|
213 Social Sciences Building, Durham, NC, 27708,
|
|
Keywords:
|
conditional moment inequalities ; quantile minimum distance ; endogeneity
|
|
Abstract:
|
Under a conditional quantile restriction, randomly censored regression models can be written in terms of conditional moment inequalities. These inequalities restrict the parameters to a set. We then show regular point identification can be achieved under a set of interpretable sufficient conditions. Our results generalize existing work on randomly censored models in that we allow for covariate dependent censoring, endogenous censoring and endogenous regressors. Maintaining the point identification conditions, we propose a quantile minimum distance estimator which converges at the parametric rate and has an asymptotically normal distribution. A small scale simulation study and an application using drug relapse data demonstrate satisfactory finite sample performance, and the ability of our proposed method to control for selective compliance.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2007 program |
