Local structural quantile effects in a model with a nonseparable control variable
I consider a semiparametric version of the nonseparable triangular model of Chesher [Chesher, A., 2003. Identification in nonseparable models. Econometrica 71, 1405-1441]. The proposed model is linear in coefficients, where the coefficients are unknown functions of unobserved latent variables. Using a control variable idea and quantile regression methods, I propose a simple two-step estimator for the coefficients evaluated at particular values of the latent variables. Under the condition that the instruments are locally relevant (i.e. they affect a particular conditional quantile of interest of the endogenous variable) I establish consistency and asymptotic normality. Simulation experiments confirm the theoretical results.
Year of publication: |
2009
|
---|---|
Authors: | Jun, Sung Jae |
Published in: |
Journal of Econometrics. - Elsevier, ISSN 0304-4076. - Vol. 151.2009, 1, p. 82-97
|
Publisher: |
Elsevier |
Keywords: | Triangular models Local instruments Control variables Quantile regression |
Saved in:
Saved in favorites
Similar items by person
-
Local structural quantile effects in a model with a nonseparable control variable
Jun, Sung Jae, (2009)
-
Weak identification robust tests in an instrumental quantile model
Jun, Sung Jae, (2008)
-
Identifying the effect of persuasion
Jun, Sung Jae, (2023)
- More ...