This thesis deals with a linear functional relationship model in which the unobserved true values satisfy multiple linear restrictions. New test statistics for some of the structural parameters of this model are derived under the assumptions that the observation vectors are normally distributed and that an estimator of the covariance matrix of measurement error is available from independent experiments or replicated observations. Exact null distributions for some test statistics proposed by other authors are also given. […]Cette thèse a pour objet l’étude de modèles fonctionnels pour lesquels les espérances de vecteurs d’observations distribués selon une loi multinormale satisfont de multiples contraintes linéaires. Supposant qu’un estimate...
AbstractThis paper provides a method of constructing multivariate distributions where both univariat...
Exact confidence regions and tests are derived for the slope parameter in some univariate and multiv...
AbstractIn this paper, to test goodness of fit to any fixed distribution of errors in multivariate l...
AbstractThis paper deals with maximum likelihood estimation of linear or nonlinear functional relati...
An estimation procedure based on estimating equations is presented for the parameters in a multivari...
AbstractMany authors have discussed maximum likelihood estimation in the simple linear functional re...
We consider the general family of multivariate normal distributions where the mean vector lies in an...
AbstractThis paper surveys the problem of estimating a linear relationship between variables which a...
AbstractThe null hypothesis that the error vectors in a multivariate linear model are independent is...
The paper examines the nature of the latent random variables which occur in linear structural models...
AbstractGeneral functional equations of the type ∑φi(Ai′t+Bi′u)=Ca(u|t)+Db(t|u)+Pk(t,u) and Σφi(Ci′t...
Typescript (photocopy).A set of multivariate observations is said to satisfy a linear functional rel...
We propose a method of comparing two functional linear models in which explana-tory variables are fu...
General functional equations of the type ∑φ<SUB>i</SUB>(A<SUB>i</SUB>'t+B<SUB>i</SUB>'u)=C<SUB>a</SU...
AbstractA multivariate linear relation ηn = β0ξn is considered, in which ξn and ηn are observed subj...
AbstractThis paper provides a method of constructing multivariate distributions where both univariat...
Exact confidence regions and tests are derived for the slope parameter in some univariate and multiv...
AbstractIn this paper, to test goodness of fit to any fixed distribution of errors in multivariate l...
AbstractThis paper deals with maximum likelihood estimation of linear or nonlinear functional relati...
An estimation procedure based on estimating equations is presented for the parameters in a multivari...
AbstractMany authors have discussed maximum likelihood estimation in the simple linear functional re...
We consider the general family of multivariate normal distributions where the mean vector lies in an...
AbstractThis paper surveys the problem of estimating a linear relationship between variables which a...
AbstractThe null hypothesis that the error vectors in a multivariate linear model are independent is...
The paper examines the nature of the latent random variables which occur in linear structural models...
AbstractGeneral functional equations of the type ∑φi(Ai′t+Bi′u)=Ca(u|t)+Db(t|u)+Pk(t,u) and Σφi(Ci′t...
Typescript (photocopy).A set of multivariate observations is said to satisfy a linear functional rel...
We propose a method of comparing two functional linear models in which explana-tory variables are fu...
General functional equations of the type ∑φ<SUB>i</SUB>(A<SUB>i</SUB>'t+B<SUB>i</SUB>'u)=C<SUB>a</SU...
AbstractA multivariate linear relation ηn = β0ξn is considered, in which ξn and ηn are observed subj...
AbstractThis paper provides a method of constructing multivariate distributions where both univariat...
Exact confidence regions and tests are derived for the slope parameter in some univariate and multiv...
AbstractIn this paper, to test goodness of fit to any fixed distribution of errors in multivariate l...