Estimation of restricted regression model when disturbances are not necessarily normal

Considering a linear regression model subject to a set of linear restrictions binding the coefficients, two classes of estimators are proposed; their risk functions with respect to a general quadratic loss function are derived under non-normality, their properties are studied and the general dominance conditions of the two classes over the restricted regression estimator are also found.

MoreLess

Year of publication:	1994
Authors:	Singh, R. Karan
Published in:	Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 19.1994, 2, p. 101-109
Publisher:	Elsevier
Keywords:	Stein estimation small [sigma] asymptotics mean squared error

More details

Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10005223078