K-Class Estimators: The Optimum Normalization for Finite Samples
- 1 June 1973
- journal article
- research article
- Published by JSTOR in Journal of the American Statistical Association
- Vol. 68 (342) , 445
- https://doi.org/10.2307/2284096
Abstract
Frequently, in estimating an equation, one is interested in a particular set of normalized coefficients. There is still a normalization problem, however, for if an equation contains m 1 endogenous variables, there are m 1 ways to estimate the same coefficients. The purpose of this article is to determine the optimum normalization for finite samples. Restricting the analysis to k-class estimators and employing Kadane's small sample technique [9], let p 2 i denote the correlation coefficient between the ith endogenous variable and the disturbance. Then, measuring “endogenousness” by p 2 i , this article shows that subject to several important qualifications, one should normalize on the most endogenous variable.Keywords
This publication has 0 references indexed in Scilit: