Identical Predictions for Different Singular Mixed Models
In linear mixed models theory one is assumed to know the structure of random effects covariance matrix. The suggestions are sometimes contradictious, especially if the model includes interactions between fixed effects and random effects. Mols  presented conditions under which two different random effects’ variance matrices will yield equal estimation and prediction results during the paper it is assumed that X is of full column rank. Wang  weakened the conditions of his theorem, and obtained the same results as his. Wang  extended Mols’s  results to situation that X is deficient in rank. Wang  gave a series of results it is assumed that X is possibly deficient in rank. They contain some necessary and sufficient theorems. We extend Wang’s [11-13] results to singular linear mixed models in this paper.
Keywordslinear mixed models best linear unbiased estimator best linear unbiased predictor robustly predictable mean square error
Unable to display preview. Download preview PDF.
- 2.Hinkelmann, K.: Resolving The Mixed Models Controversy, Comments. Am. Stat. 54, 228 (2000)Google Scholar
- 4.Neter, J., Wasserman, W., Kutner, M.H.: Applied Linear Statistical Models, 3rd edn. CRC Press (1990)Google Scholar
- 6.SAS Institute Inc.: SAS Onlinedoc. Version 8. Cary, NC, SAS Institute Inc. (1999) Google Scholar
- 7.Scheffe, H.: The Analysis of Variance. Wiley (1959)Google Scholar
- 8.Searle, S.R.: Linear Models. Wiley (1971)Google Scholar
- 10.Wolfinger, R., Stroup, W.W.: Resolving the Mixed Models Controversy, Comments. Am. Stat. 54, 228 (2000)Google Scholar
- 11.Wang, S.Q.: Constraints on Random Effects and Linear Mixed Model Predictions. In: Proceedings of the 7th Conference on Biological Dynamic System and Stability of Differential Equation, pp. 260–263. World Academic Press, Liverpool (2010)Google Scholar
- 12.Wang, S.Q.: Constraints on Random Effects and Mixed Model Predictions with the Coefficient Matrix of Deficient in Rank. In: Proceedings of Third International Conference on Modelling and Simulation. Applied Mathematics and Mathematical Modelling, vol. 5, pp. 88–91. World Academic Press, Liverpool (2010)Google Scholar
- 13.Wang, S.Q.: The Conditions with Different Models Having Identical Predictions. In: Advances on Probability and Statistics, pp. 183–186. World Academic Press, Liverpool (2010)Google Scholar