Approximate design-based variance of functions of covariance matrix

Authors

  • Imbi Traat University of Tartu

DOI:

https://doi.org/10.12697/ACUTM.2004.08.22

Keywords:

finite population, sampling, covariance matrix, determinant, Hotelling's T^2, Taylor linearization

Abstract

Functions of a design-weighted estimator ^ S  of the finite population covariance matrix are considered. For these functions (determinant, Hotelling’s T2) the approximate (Taylor series based) variances are derived. For ^ S also the exact dispersion matrix is derived. These are generalizations of earlier results for independent identically distributed (i.i.d.) variables. A simulation study supports the derived formulae.

Downloads

Download data is not yet available.

Author Biography

Imbi Traat, University of Tartu

Institute of Mathematical Statistics

Downloads

Published

2004-12-31

Issue

Section

Articles