Ferreira, DárioFerreira, Sandra S.Nunes, CéliaMexia, João T.2020-02-072020-02-072018http://hdl.handle.net/10400.6/9133This paper deals with the estimability of variance components, in mixed models, when the dimension of the commutative algebra, spanned by all possible variance-covariance matrices, is greater than the number of linearly independente unknown variance components. As example we present an application to a random three-factor crossed-model.engInferenceLinear modelsVariance componentsSegregation and intrinsec restrictions on canonic variance componentsjournal article10.1063/1.5044064