Finite sample properties of adaptive regression estimators

Pin T. Ng

doi:10.1080/07474939508800321

Finite sample properties of adaptive regression estimators

Pin T. Ng

Business, The W.A. Franke College of (CoB)

Research output: Contribution to journal › Article › peer-review

Abstract

The finite sample properties of adaptive M- and L-estimators for the linear regression model are studied through extensive Monte Carlo simulations. We provide guidelines for choosing the trimming proportion and estimating the score function for adaptive L-estimators. Suggestions are also given on choosing the trimming parameters, the score function estimators, the initial n-consistent estimator and estimating the Fisher information in the construction of adaptive M-estimators. We also investigate the effect of design dimension on the various adaptive estimators and the accuracy of the estimated standard errors.

Original language	English (US)
Pages (from-to)	267-297
Number of pages	31
Journal	Econometric Reviews
Volume	14
Issue number	3
DOIs	https://doi.org/10.1080/07474939508800321
State	Published - Jan 1 1995

Keywords

Adaptive estimators
Finite sample
Iterative adaptive estimators
Ro-
Score function
bust estimators

ASJC Scopus subject areas

Economics and Econometrics

Access to Document

10.1080/07474939508800321

Cite this

@article{93b2d104e376452f9e1e92583dc34175,

title = "Finite sample properties of adaptive regression estimators",

abstract = "The finite sample properties of adaptive M- and L-estimators for the linear regression model are studied through extensive Monte Carlo simulations. We provide guidelines for choosing the trimming proportion and estimating the score function for adaptive L-estimators. Suggestions are also given on choosing the trimming parameters, the score function estimators, the initial n-consistent estimator and estimating the Fisher information in the construction of adaptive M-estimators. We also investigate the effect of design dimension on the various adaptive estimators and the accuracy of the estimated standard errors.",

keywords = "Adaptive estimators, Finite sample, Iterative adaptive estimators, Ro-, Score function, bust estimators",

author = "Ng, \{Pin T.\}",

note = "Funding Information: 6. ACKNOWLEDGMENTS The author would like to thank Roger Koenker, Essie Maasoumi, and Robin Sickle for their generous comments. Suggestions and comments by two anonymous referees, which lead to addition of the extended designs of the Monte Carlo simulations and a much improved paper, are also gratefully acknowledged. Second portion of the simulations in this paper was performed on computing facilities supported in part by the National Science Foundation Grants SES 89-22472.",

year = "1995",

month = jan,

day = "1",

doi = "10.1080/07474939508800321",

language = "English (US)",

volume = "14",

pages = "267--297",

journal = "Econometric Reviews",

issn = "0747-4938",

publisher = "Taylor and Francis Ltd.",

number = "3",

}

TY - JOUR

T1 - Finite sample properties of adaptive regression estimators

AU - Ng, Pin T.

N1 - Funding Information: 6. ACKNOWLEDGMENTS The author would like to thank Roger Koenker, Essie Maasoumi, and Robin Sickle for their generous comments. Suggestions and comments by two anonymous referees, which lead to addition of the extended designs of the Monte Carlo simulations and a much improved paper, are also gratefully acknowledged. Second portion of the simulations in this paper was performed on computing facilities supported in part by the National Science Foundation Grants SES 89-22472.

PY - 1995/1/1

Y1 - 1995/1/1

N2 - The finite sample properties of adaptive M- and L-estimators for the linear regression model are studied through extensive Monte Carlo simulations. We provide guidelines for choosing the trimming proportion and estimating the score function for adaptive L-estimators. Suggestions are also given on choosing the trimming parameters, the score function estimators, the initial n-consistent estimator and estimating the Fisher information in the construction of adaptive M-estimators. We also investigate the effect of design dimension on the various adaptive estimators and the accuracy of the estimated standard errors.

AB - The finite sample properties of adaptive M- and L-estimators for the linear regression model are studied through extensive Monte Carlo simulations. We provide guidelines for choosing the trimming proportion and estimating the score function for adaptive L-estimators. Suggestions are also given on choosing the trimming parameters, the score function estimators, the initial n-consistent estimator and estimating the Fisher information in the construction of adaptive M-estimators. We also investigate the effect of design dimension on the various adaptive estimators and the accuracy of the estimated standard errors.

KW - Adaptive estimators

KW - Finite sample

KW - Iterative adaptive estimators

KW - Ro-

KW - Score function

KW - bust estimators

UR - https://www.scopus.com/pages/publications/84952402210

UR - https://www.scopus.com/inward/citedby.url?scp=84952402210&partnerID=8YFLogxK

U2 - 10.1080/07474939508800321

DO - 10.1080/07474939508800321

M3 - Article

AN - SCOPUS:84952402210

SN - 0747-4938

VL - 14

SP - 267

EP - 297

JO - Econometric Reviews

JF - Econometric Reviews

IS - 3

ER -

Finite sample properties of adaptive regression estimators

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this