For Factor Analysis we have terms and definitions in 5 topics. The topics are Anthromorphemics, Anthropology, Finance, Marketing and Ordination.

Factor Analysis (Anthromorphemics)

A multivariate statistical technique which assesses the degree of variation between artifact types, and is based on a matrix of correlation coefficients which measure the relative association between any two variables.

Factor Analysis (Anthropology)

A multivariate statistical technique which assesses the degree of variation between artifact types, and is based on a matrix of correlation coefficients which measure the relative association between any two variables.

Factor Analysis (Finance)

A statistical procedure that seeks to explain a certain phenomenon, such as the return on a common stock, in terms of the behavior of a set of predictive factors.

Factor Analysis (Marketing)

Procedure for data simplification through reducing the many rating scales (or set of variables) used by the researcher to a smaller set of factors or composite variables by identifying dimensions underlying the data.

Factor Analysis (Ordination)

This is a term which has been variously defined. In some treatments it seems to be a synonym of ordination. Sometimes (as in some statistical software) it includes principal components analysis. The following discussion is from Morrison (1967); my comments are in brackets.
* "It would seem clear that a new class of techniques [Morrison had just finished discussing partial correlation, multiple correlation, and canonical correlation] will be required for picking apart the dependence structure when the responses are symmetric in nature or no a priori patterns of causality are available [amongst all variables of interest]. Those methods fall under the general heading of factor analysis, for by them one attempts to descry those hidden factors which have generated the dependence or variation in the responses. That is, the observable, or manifest variates are represented as functions of a smaller number of latent factor variates.
According to Gauch (1982), there is a subtle distinction between ordination and factor analysis, which appears consistent with Morrison:
* "Factor analysis is similar to principal components analysis, except that instead of trying to account for as much of the total variance as possible, only correlations between variables are of interest as reflecting putative underlying causes or factors"

Similar

Browse words that start with:

• Fa
• Fac
• Fact
• Facto

Browse All Terms by First Letter

Term Search