[PDF][PDF] VECM analysis in JMulTi

H Lütkepohl, M Krätzig - Recuperado de http://www. jmulti. de/download …, 2005 - jmulti.de
2.1 Background There are different estimation procedures available for estimating a model
of the type (1), depending on the precise model specification. If Γ0= I, there are no zero …

Computation of variance components by the MINQUE method

J Kleffe, B Seifert - Journal of multivariate analysis, 1986 - Elsevier
We present a new method of computing CR Rao's MINQUE in variance component models
(y= Xβ+ U 1 ξ 1+…+ U p ξ p), which requires only inversion and storage of ni× ni matrices …

REML estimation of covariance matrices with restricted parameter spaces

JA Calvin, RL Dykstra - Journal of the American Statistical …, 1995 - Taylor & Francis
Restricted parameter spaces for covariance matrices, such as∑= σ2 I or∑= α I+ β J, are
often used to simplify estimation. In addition, fixed upper and/or lower bounds may be …

Estimation of structural equation models with factors by EM algorithm

M Tami, X Bry, C Lavergne - HAL, 2014 - dml.mathdoc.fr
Introduits dans les années 1970 par Jöreskog, les modèles d'équations struc-turelles à
facteurs permettent de mettre en relation des variables non observables, dites la-tentes. À …

The reduced form of recursive models: Small sample properties

H Schneeweiss - Linear algebra and its applications, 1996 - Elsevier
The reduced form of a recursive multiequation model can be estimated either directly by
ordinary least squares (OLS) or indirectly by first estimating the structural form, equation by …

[图书][B] A comparison of estimators in Hierarchical Linear Modeling: Restricted maximum likelihood versus bootstrap via minimum norm quadratic unbiased estimators

AN Delpish - 2006 - search.proquest.com
The purpose of the study was to investigate the relative performance of two estimation
procedures, the restricted maximum likelihood (REML) and the bootstrap via MINQUE, for a …

Matrix free computation of CR Rao's MINQUE for unbalanced nested classification models

J Kleffé, B Seifert - Computational Statistics & Data Analysis, 1984 - Elsevier
This paper presents an efficient algorithm for computation of MINQUE, best linear unbiased
estimates of fixed effects and best linear predictors of random effects, which is based on …

Least squares estimation of covariance matrices in balanced multivariate variance components models

JA Calvin, RL Dykstra - Journal of the American Statistical …, 1991 - Taylor & Francis
The problem of estimating covariance matrices in balanced multivariate variance
components models is discussed. As with univariate models, it is possible for the traditional …

Evaluating Pseudo-R2's for binary probit models

MR Veall, KF Zimmermann - Quality and Quantity, 1994 - Springer
Many applied researchers of limited dependent variable models found it disadvantageous
that a widely accepted Pseudo-R 2 does not exist for this type of estimation. The paper …

An algorithm for restricted maximum likelihood estimation in balanced multivariate variance components models

JA Calvin, RL Dykstra - Journal of Statistical Computation and …, 1992 - Taylor & Francis
Restricted maximum likelihood (REML) estimation of variance components in multivariate
linear models is a computationally intensive task. Calvin and Dykstra (1991a) have …