Preliminary test approach in high dimensional multivariate regression models

Abstract

In this paper, we consider the multivariate linear regression model in view of high dimensional data. We formulate the preliminary test approach by estimating the location parameter when it is apriori suspected that may be equal to zero. Then use derive bias, quadratic bias and risk expression through making use of a refinement of test statistic to accommodate the high-dimensional assumption. We support our result by a simulation as well as a real example.

Mina Norouzirad

Researcher

A dedicated researcher and educator in the field of statistics