Modelos factoriales para datos longitudinales con estructuras comunes y especificas

Metodología de las Ciencias del Comportamiento 01/2004; Sup..

ABSTRACT One of the most useful techniques to analyse latent structures is exploratory Factor Analysis. When several data matrices, arising from different occasions and/or groups, are obtained, the comparison and integration of the resulting latent spaces is an important task. In this paper we propose a factor model for several groups that includes shared common factors for all the groups and specific factors for each group. Shared common factors are obtained from the common directions of the separated latent subspaces and specific factors from the residuals after projecting the group onto the common subspace

1 Bookmark
  • [Show abstract] [Hide abstract]
    ABSTRACT: SupposeP i (i) (i = 1, 2, ...,m, j = 1, 2, ...,n) give the locations ofmn points inp-dimensional space. Collectively these may be regarded asm configurations, or scalings, each ofn points inp-dimensions. The problem is investigated of translating, rotating, reflecting and scaling them configurations to minimize the goodness-of-fit criterion i=1 m i=1 n 2(P j (i) G i ), whereG i is the centroid of them pointsP i (i) (i = 1, 2, ...,m). The rotated positions of each configuration may be regarded as individual analyses with the centroid configuration representing a consensus, and this relationship with individual scaling analysis is discussed. A computational technique is given, the results of which can be summarized in analysis of variance form. The special casem = 2 corresponds to Classical Procrustes analysis but the choice of criterion that fits each configuration to the common centroid configuration avoids difficulties that arise when one set is fitted to the other, regarded as fixed.
    Psychometrika 01/1975; 40(1):33-51. · 2.21 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: There is a truism about applied research that an inadequate concept of change leads to diminished or misguided applied research. Hence this paper urges distinguishing kinds of change, distinctions which are suggested by experience and also are supported with evidence generated by exotic statistical and computational techniques in which we have been engaged. An immediate pay-off of making such distinctions is more definite reliance on existing research findings, whose interpretation is necessarily related to their underlying concept of change. More central still, the goal is to facilitate the design and evaluation of efforts to improve the human condition and the quality of life, especially in organizations.Initially, conceptual clarification of "change" will show that at least three kinds seem distinguishable. Later, data from a study of a "successful" Flexi-Time intervention will be used to test these conceptual clarifications. Detailed statistical analysis will support the broad position that a unitary concept of change is inappropriate and may be seriously misleading.
    J Appl Behav Sci. 01/1976;
  • [Show abstract] [Hide abstract]
    ABSTRACT: This article generalizes the method of principal components to so-called “common principal components” as follows: Consider the hypothesis that the covariance matrices Σi for k populations are simultaneously diagonalizable. That is, there is an orthogonal matrix β such that β' Σiβ is diagonal for i = 1, …, k. I derive the normal-theory maximum likelihood estimates of the common component Σi matrices and the log-likelihood-ratio statistics for testing this hypothesis. The solution has some favorable properties that do not depend on normality assumptions. Numerical examples illustrate the method. Applications to data reduction, multiple regression, and nonlinear discriminant analysis are sketched.
    Journal of the American Statistical Association 12/1984; 79(388):892-898. · 1.83 Impact Factor


Available from
Jun 3, 2014