TY - JOUR
T1 - Amemiya's form of the weighted least squares estimator
AU - Koenker, Roger
AU - Machado, José A. F.
AU - Skeels, Christopher L.
AU - Welsh, A. H.
PY - 1993/1/1
Y1 - 1993/1/1
N2 - Amemiya's estimator is a weighted least squares estimator of the regression coefficients in a linear model with heteroscedastic errors. It is attractive because the heteroscedasticity is not parametrized and the weights (which depend on the error covariance matrix) are estimated nonparametrically. This paper derives an asymptotic expansion for Amemiya's form of the weighted least squares estimator, and uses it to discuss the effects of estimating the weights, of the number of iterations, and of the choice of the initial estimate. The paper also discusses the special case of normally distributed errors and clarifies the particular consequences of assuming normality.
AB - Amemiya's estimator is a weighted least squares estimator of the regression coefficients in a linear model with heteroscedastic errors. It is attractive because the heteroscedasticity is not parametrized and the weights (which depend on the error covariance matrix) are estimated nonparametrically. This paper derives an asymptotic expansion for Amemiya's form of the weighted least squares estimator, and uses it to discuss the effects of estimating the weights, of the number of iterations, and of the choice of the initial estimate. The paper also discusses the special case of normally distributed errors and clarifies the particular consequences of assuming normality.
KW - heteroscedasticity
KW - robustness
KW - Weighted least squares
UR - http://www.scopus.com/inward/record.url?scp=84990495169&partnerID=8YFLogxK
U2 - 10.1111/j.1467-842X.1993.tb01322.x
DO - 10.1111/j.1467-842X.1993.tb01322.x
M3 - Article
AN - SCOPUS:84990495169
SN - 0004-9581
VL - 35
SP - 155
EP - 174
JO - Australian Journal of Statistics
JF - Australian Journal of Statistics
IS - 2
ER -