THE SAMPLING PERFORMANCE OF INEQUALITY RESTRICTED AND PRE‐TEST ESTIMATORS IN A MIS‐SPECIFIED LINEAR MODEL

Alan T.K. Wan

doi:10.1111/j.1467-842X.1994.tb00884.x

THE SAMPLING PERFORMANCE OF INEQUALITY RESTRICTED AND PRE‐TEST ESTIMATORS IN A MIS‐SPECIFIED LINEAR MODEL

Alan T.K. Wan

Research output: Journal Publications and Reviews › RGC 22 - Publication in policy or professional journal

14 Citations (Scopus)

Abstract

The literature on the sampling properties of the inequality restricted and pre‐test estimators typically assumes a properly specified model and focuses on the estimation of the regression coefficient vector. In this paper, we derive and evaluate the risk functions of these estimators for both the prediction vector and the disturbance variance in a model which is mis‐specified through the exclusion of relevant regressors. The results suggest that unrestricted estimation is generally preferable to pre‐testing or naively imposing restrictions. Copyright © 1994, Wiley Blackwell. All rights reserved

Original language	English
Pages (from-to)	313-325
Journal	Australian Journal of Statistics
Volume	36
Issue number	3
DOIs	https://doi.org/10.1111/j.1467-842X.1994.tb00884.x
Publication status	Published - Sept 1994
Externally published	Yes

Research Keywords

Inequality restriction
mis‐specification
pre‐test
squared error loss

Access Output

10.1111/j.1467-842X.1994.tb00884.x

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{7fffefe6ae664e73a1f8bdae2e2bcb25,

title = "THE SAMPLING PERFORMANCE OF INEQUALITY RESTRICTED AND PRE‐TEST ESTIMATORS IN A MIS‐SPECIFIED LINEAR MODEL",

abstract = "The literature on the sampling properties of the inequality restricted and pre‐test estimators typically assumes a properly specified model and focuses on the estimation of the regression coefficient vector. In this paper, we derive and evaluate the risk functions of these estimators for both the prediction vector and the disturbance variance in a model which is mis‐specified through the exclusion of relevant regressors. The results suggest that unrestricted estimation is generally preferable to pre‐testing or naively imposing restrictions. Copyright {\textcopyright} 1994, Wiley Blackwell. All rights reserved",

keywords = "Inequality restriction, mis‐specification, pre‐test, squared error loss",

author = "Wan, \{Alan T.K.\}",

year = "1994",

month = sep,

doi = "10.1111/j.1467-842X.1994.tb00884.x",

language = "English",

volume = "36",

pages = "313--325",

journal = "Australian Journal of Statistics",

issn = "0004-9581",

publisher = "Statistical Society of Australia",

number = "3",

}

TY - JOUR

T1 - THE SAMPLING PERFORMANCE OF INEQUALITY RESTRICTED AND PRE‐TEST ESTIMATORS IN A MIS‐SPECIFIED LINEAR MODEL

AU - Wan, Alan T.K.

PY - 1994/9

Y1 - 1994/9

N2 - The literature on the sampling properties of the inequality restricted and pre‐test estimators typically assumes a properly specified model and focuses on the estimation of the regression coefficient vector. In this paper, we derive and evaluate the risk functions of these estimators for both the prediction vector and the disturbance variance in a model which is mis‐specified through the exclusion of relevant regressors. The results suggest that unrestricted estimation is generally preferable to pre‐testing or naively imposing restrictions. Copyright © 1994, Wiley Blackwell. All rights reserved

AB - The literature on the sampling properties of the inequality restricted and pre‐test estimators typically assumes a properly specified model and focuses on the estimation of the regression coefficient vector. In this paper, we derive and evaluate the risk functions of these estimators for both the prediction vector and the disturbance variance in a model which is mis‐specified through the exclusion of relevant regressors. The results suggest that unrestricted estimation is generally preferable to pre‐testing or naively imposing restrictions. Copyright © 1994, Wiley Blackwell. All rights reserved

KW - Inequality restriction

KW - mis‐specification

KW - pre‐test

KW - squared error loss

UR - https://www.scopus.com/pages/publications/84990504420

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84990504420&origin=recordpage

U2 - 10.1111/j.1467-842X.1994.tb00884.x

DO - 10.1111/j.1467-842X.1994.tb00884.x

M3 - RGC 22 - Publication in policy or professional journal

SN - 0004-9581

VL - 36

SP - 313

EP - 325

JO - Australian Journal of Statistics

JF - Australian Journal of Statistics

IS - 3

ER -

THE SAMPLING PERFORMANCE OF INEQUALITY RESTRICTED AND PRE‐TEST ESTIMATORS IN A MIS‐SPECIFIED LINEAR MODEL

Abstract

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this