IMPROVING THE EFFICIENCY AND ROBUSTNESS OF THE SMOOTHED MAXIMUM SCORE ESTIMATOR

Francisco Alvarez-Cuadrado ()

Departmental Working Papers from McGill University, Department of Economics

Abstract: The binary-response maximum score (MS) estimator is a robust estimator, which can accommodate heteroskedasticity of an unknown form; J. Horowitz (1992) defined a smoothed maximum score estimator SMS) and demonstrated that this improves the convergence rate for sufficiently smooth conditional error densities. In this paper we relax Horowitz’s smoothness assumptions of the model and extend his asymptotic results. We also derive a joint limiting distribution of estimators with different bandwidths and smoothing kernels. We construct an estimator that combines SMS estimators for different bandwidths and kernels to overcome the uncertainty over choice of bandwidth when the degree of smoothnes of error distribution is unknown. A Monte Carlo study demonstrates the gains in efficiency and robustness.

JEL-codes: C14 C25 (search for similar items in EconPapers)
Pages: 34 pages
Date: 2006-09
New Economics Papers: this item is included in nep-dcm and nep-ecm
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.mcgill.ca/files/economics/msdec21.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:mcl:mclwop:2004-01

Access Statistics for this paper

More papers in Departmental Working Papers from McGill University, Department of Economics Contact information at EDIRC.
Bibliographic data for series maintained by Shama Rangwala ( this e-mail address is bad, please contact ).