Total shrinkage versus partial shrinkage in multiple linear regression

  • Eshetu Wencheko Department of Statistics, Faculty of Science Addis Ababa University, PO Box 1176, Addis Ababa, Ethiopia
Keywords: Partial and total shrinkage, variance inflation factors

Abstract



The paper discusses the merits of partial shrinkage of the ordinary least square estimator of the coefficients of the multiple regression model of full rank. Theoretical comparisons of scalar and matrix-valued risks of the partially shrunken and totally shrunken estimators are given. The strategy of partial shrinkage is applied to two data sets.

SINET: Ethiopian Journal of Science Vol. 23, No. 1 (June 2000), pp. 67-72

Key words/phrases: Partial and total shrinkage, variance inflation factors
Published
2004-06-09
Section
Articles

Journal Identifiers


eISSN: 2520-7997
print ISSN: 0379-2897