On modified minimum variance quadratic unbiased estimation (MIVQUE) of variance components in mixed linear models

Article type: Research Article

Authors: Subramani, J.

Affiliations: Department of Statistics, Pondicherry University, R V Nagar, Kalapet, Puducherry- 605 014, India. E-mail: [email protected]

Abstract: The present paper deals with some modifications on the computational aspects of MIVQUE of variance components in mixed linear models. As a result two modified MIVQU estimators namely (MIVQUE I and MIVQUE II) are introduced. Further the relative performances of Modified MIVQU estimators are assessed with that of Mitra Type Estimators (MTE) and MIVQU estimators for unbalanced one way random model based on different optimality criteria with various n-patterns.

Keywords: ANOVA, MTE, MIVQUE, Modified MIVQUE, T-Optimality, D-Optimality, M-Optimality, variance components

DOI: 10.3233/MAS-2012-0225

Journal: Model Assisted Statistics and Applications, vol. 7, no. 3, pp. 179-200, 2012