Combining Independent Estimators and Estimation in Linear Regression with Unequal Variances

Rao, J. N. K.; Kocherlakota, S.

doi:10.2307/2528832

Cited by 65 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results ( 1) and (ii) are discussed in Scaly ( 1970) , Rao (1970Rao ( , 1971 and Focke and Dowses ( 1972) and (iii) in Pincus (1974). where B is any choice of X~' , i.e., B is a matrix of maximum rank such that B 'X -0.…”

Section: Estimability 3 1 Unbiasednessmentioning

confidence: 91%

1 Estimation of variance components

Rao¹,

Kleffe²

1980

Handbook of Statistics

View full text Add to dashboard Cite

Section: Estimability 3 1 Unbiasednessmentioning

confidence: 91%

1 Estimation of variance components

Rao¹,

Kleffe²

1980

Handbook of Statistics

View full text Add to dashboard Cite

“…The problem, however, arises when data enough to estimate the error variances are not available. In this case, as indicated by Rao and Subrahmaniam (1971) and Rao (1980), the information included in sample means may be useful so as to get estimators with higher accuracy. Although the estimation issue given in this paper is limited to a simpler situation, the obtained results suggest a possibility of constructing estimators with higher efficiency in more general setting.…”

Section: Introductionmentioning

confidence: 99%

Double Shrinkage Estimation of Common Coefficients in Two Regression Equations with Heteroscedasticity

Kubokawa

1998

Journal of Multivariate Analysis

View full text Add to dashboard Cite

The problem of estimating the common regression coefficients is addressed in this paper for two regression equations with possibly different error variances. The feasible generalized least squares (FGLS) estimators have been believed to be admissible within the class of unbiased estimators. It is, nevertheless, established that the FGLS estimators are inadmissible in light of minimizing the covariance matrices if the dimension of the common regression coefficients is greater than or equal to three. Double shrinkage unbiased estimators are proposed as possible candidates of improved procedures. Academic PressAMS 1991 subject classifications: primary 62C15; secondary 62F11, 62H12, 62J05.

show abstract

“…Several authors have described error variancecovariance structures for which there is a single best LUE of an estimable function (see Mitra and Rao 1969 ;Rao 1971 ;Seely and Zyskind 1971 ;Zyskind 1967Zyskind , 1969Zyskind , 1973Zyskind and Martin 1969). Others have prescribed procedures in which an estimated dispersion matrix is used in weighted least squares, resulting in nonlinear estimators to which the conclusions of linear models theory do not apply (see Hildreth and Houck 1968; Maddala and Mount 1973;Rao 1967Rao , 1970; Rao and Subrahmaniam 1971);…”

Section: Introductionmentioning

confidence: 99%