Open Access
December, 1988 Optimum Tests in Unbalanced Two-Way Models without Interaction
Thomas Mathew, Bimal Kumar Sinha
Ann. Statist. 16(4): 1727-1740 (December, 1988). DOI: 10.1214/aos/1176351065

Abstract

It is an open problem in the literature to derive optimum tests for the equality of treatment effects in an unbalanced two-way classification model. For such models without interaction, optimum tests are derived in the following cases: (i) the locally best invariant unbiased test for the random effects model corresponding to an equiblock and equireplicate design, (ii) the locally best invariant unbiased test for the mixed effects model with mixed treatment effects corresponding to a balanced incomplete block design and (iii) the uniformly most powerful invariant test or the locally best invariant test for the mixed effects model with random treatment effects. Robustness of the optimum invariant tests against suitable deviations from normality is also indicated.

Citation

Download Citation

Thomas Mathew. Bimal Kumar Sinha. "Optimum Tests in Unbalanced Two-Way Models without Interaction." Ann. Statist. 16 (4) 1727 - 1740, December, 1988. https://doi.org/10.1214/aos/1176351065

Information

Published: December, 1988
First available in Project Euclid: 12 April 2007

zbMATH: 0653.62018
MathSciNet: MR964950
Digital Object Identifier: 10.1214/aos/1176351065

Subjects:
Primary: 62F03
Secondary: 62F04 , 62K10

Keywords: Balanced incomplete block design , Locally best invariant test , locally best invariant unbiased test , uniformly most powerful invariant test , variance balanced design

Rights: Copyright © 1988 Institute of Mathematical Statistics

Vol.16 • No. 4 • December, 1988
Back to Top