Dispersion Matrices for Variance Components Models
- 1 June 1979
- journal article
- theory and-method
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 74 (366a) , 465-470
- https://doi.org/10.1080/01621459.1979.10482540
Abstract
The dispersion matrix of balanced data in a two-way crossed-classification variance-components model is generalized to the case of any balanced-data variance-components model, consisting of crossed and/or nested classifications. The eigenvalues, determinant and inverse, of this generalized matrix are derived.Keywords
This publication has 7 references indexed in Scilit:
- Estimation of linear models with crossed-error structureJournal of Econometrics, 1974
- Best quadratic unbiased estimators of the variance-covariance matrix in normal regressionJournal of Econometrics, 1973
- Wanted: an inverse matrixCommunications in Statistics, 1973
- Notes on the Covariance Matrix of a Random, Nested Anova ModelThe Annals of Mathematical Statistics, 1972
- Quadratic Subspaces and CompletenessThe Annals of Mathematical Statistics, 1971
- A Note on Error Components ModelsEconometrica, 1971
- The Use of Error Components Models in Combining Cross Section with Time Series DataEconometrica, 1969