Lešanská, Eva Insensitivity regions for estimators of mean value parameters in mixed models with constraints. (English) Zbl 1001.62012 Tatra Mt. Math. Publ. 22, 37-49 (2001). The author considers a regular normal mixed linear model with variance components under constraints. Because only locally best estimators are available in most situations, sensitivity of the estimators of the first order (mean value) parameters to small changes in the second order (variance components) parameters is studied. Explicit results for insensitivity regions for both point estimators and confidence regions are given. Reviewer: Ivan Žežula (Košice) Cited in 3 Documents MSC: 62F10 Point estimation 62F30 Parametric inference under constraints 62F25 Parametric tolerance and confidence regions 62J10 Analysis of variance and covariance (ANOVA) Keywords:mixed linear models with constraints; insensitivity (nonsensitiveness) regions; variance components × Cite Format Result Cite Review PDF