New Estimation of Variance Components in Two-way Classification Model with Random Effects
Xu Wangli · Gongcheng shuxue xuebao · 2009
That two-way classification model with random effects is used widely in practice,one of the most important estimation methods for this model is analysis of variance estimate (ANOVA). Notice that the mean square error (MSE) of the ANOVA is not the smallest,we propose an improved ANOVA based on new estimation family and prove that the MSE of the new estimator is smaller than that of ANOVA. The estimation method is extended to general models,which are used mainly in the field of medicine.