<Articles>On the Sensitivity of Tests of the Mean-Variance Efficiency

概要

論文の詳細を見る
This paper is concerned with the sensitivity of tests of the mean-variance efficiency of a portfolio to different sets of assets. Since it is impossible in practice to include all existing assets for tests of the efficiency of a given portfolio, we are always confronted to the question of what happens to the inference if the efficiency is tested in a larger set of assets. This paper investigates the addition of what kind of asset inverses the inference of the efficiency. The inversion of the inference depends on the degree of the orthogonality between the excess return of the added asset and the excess returns of the original assets. In a linear regression of the excess return of the added asset onto the excess returns of the original assets, if the variation of the intercept term is large relative to the variation of the disturbance term, then the inclusion of such an asset likely inverses the inference in which the portfolio was inferred as efficient with respect to the original set of assets.
青森公立大学の論文
1996-03-11