Use of minimum risk approach in the estimation of regression models with missing observations

被引：0

作者：

Toutenburg H. ^{[1
]}

Shalabh ^{[2
]}

机构：

[1] Institut für Statistik, Universität München, 80799 München

[2] Department of Statistics, Panjab University

来源：

Metrika | 2002年 / 54卷 / 3期

关键词：

Biased imputation; Imcomplete response; Minimum risk criterion; Regression; Small disturbance asymptotics;

D O I：

10.1007/s184-002-8367-y

中图分类号：

学科分类号：

摘要：

This article considers a linear regression model with some missing observations on the response variable and presents two estimators of regression coefficients employing the approach of minimum risk estimation. Small disturbance asymptotic properties of these estimators along with the traditional unbiased estimator are analyzed and conditions, that are easy to check in practice, for the superiority of one estimator over the other are derived.

引用

页码：247 / 259

页数：12

共 5 条

[1] Guilkey D.K., Price J.M., On comparing restricted least squares estimators, Journal of Econometrics, 15, pp. 397-404, (1981)
[2] Little R.J.A., Regression with missing X's: A review, Journal of the American Statistical Association, 87, pp. 1227-1237, (1992)
[3] Little R.J.A., Rubin D.B., Statistical Analysis with Missing Data, (1987)
[4] Rao C.R., Toutenburg H., Linear Models: Least Squares and Alternatives. 2 Edn, (1999)
[5] Yancey T.A., Judge G.G., Bock M.E., A mean square error test when stochastic restrictions are used in regression, Communications in Statistics, Part A - Theory and Methods, 3, pp. 755-768, (1974)

← 1 →