TY - JOUR
T1 - An iterative feasible minimum mean squared error estimator of the disturbance variance in linear regression under asymmetric loss *
AU - Wan, Alan T.K.
AU - Kurumai, Hiroko
PY - 1999/11/15
Y1 - 1999/11/15
N2 - In this article, we consider the risk performance of an iterative feasible minimum mean squared error estimator of the regression disturbance variance under the LINEX loss function. This loss is a generalisation of the quadratic loss function allowing for asymmetry. Notwithstanding the justification for using the feasible minimum mean squared error estimator in estimating the regression coefficients, it is found that the corresponding estimator of the disturbance variance does not, in general, improve over a class of conventional estimators commonly used in practice. © 1999 Elsevier Science B.V.
AB - In this article, we consider the risk performance of an iterative feasible minimum mean squared error estimator of the regression disturbance variance under the LINEX loss function. This loss is a generalisation of the quadratic loss function allowing for asymmetry. Notwithstanding the justification for using the feasible minimum mean squared error estimator in estimating the regression coefficients, it is found that the corresponding estimator of the disturbance variance does not, in general, improve over a class of conventional estimators commonly used in practice. © 1999 Elsevier Science B.V.
KW - Error variance
KW - LINEX loss
KW - Minimum mean squared error
KW - Risk
UR - http://www.scopus.com/inward/record.url?scp=0033570867&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0033570867&origin=recordpage
U2 - 10.1016/s0167-7152(99)00065-6
DO - 10.1016/s0167-7152(99)00065-6
M3 - 21_Publication in refereed journal
VL - 45
SP - 253
EP - 259
JO - Statistics and Probability Letters
JF - Statistics and Probability Letters
SN - 0167-7152
IS - 3
ER -