The authors are grateful to three anonymous referees for their valuable comments and suggestions. This research is supported by The Gregory C. Chow Econometric Research Program at Princeton University (Aradillas-Lopez and Honoré), the NSF grant No. SES-0417895 and the Danish National Research Foundation, through CAM at The University of Copenhagen (Honoré). Please address correspondence to: Andres Aradillas-Lopez, Department of Economics, Princeton University, Princeton, NJ 08544. E-mail: aaradill@princeton.edu.
1468-2354/asset/IERE_centre.gif?v=1&s=0c315c019499e503c6ee8beebeaf22509be89282)
PAIRWISE DIFFERENCE ESTIMATION WITH NONPARAMETRIC CONTROL VARIABLES†
Article first published online: 11 DEC 2007
DOI: 10.1111/j.1468-2354.2007.00457.x
Additional Information
How to Cite
Aradillas-Lopez, A., Honoré, B. E. and Powell, J. L. (2007), PAIRWISE DIFFERENCE ESTIMATION WITH NONPARAMETRIC CONTROL VARIABLES. International Economic Review, 48: 1119–1158. doi: 10.1111/j.1468-2354.2007.00457.x
- †
Manuscript received December 2005; revised February 2007.
Publication History
- Issue published online: 11 DEC 2007
- Article first published online: 11 DEC 2007
- Abstract
- Article
- References
- Cited By
This article extends the pairwise difference estimators for various semilinear limited dependent variable models proposed by Honoré and Powell (Identification and Inference in Econometric Models. Essays in Honor of Thomas Rothenberg Cambridge: Cambridge University Press, 2005) to permit the regressor appearing in the nonparametric component to itself depend upon a conditional expectation that is nonparametrically estimated. This permits the estimation approach to be applied to nonlinear models with sample selectivity and/or endogeneity, in which a “control variable” for selectivity or endogeneity is nonparametrically estimated. We develop the relevant asymptotic theory for the proposed estimators and we illustrate the theory to derive the asymptotic distribution of the estimator for the partially linear logit model.