The measurement error in principal components extracted from a set of fallible measures is discussed and evaluated. It is shown that as long as one or more measures in a given set of observed variables contains error of measurement, so also does any principal component obtained from the set. The error variance in any principal component is shown…

Exploratory factor analysis involves five key decisions. The second decision, how many factors to retain, is the focus of the current paper. Extracting too many or too few factors often leads to devastating effects on study results. The advantages and disadvantages of the most effective and/or most utilized strategies to determine the number of…

In large-scale educational surveys, a latent regression model is used to compensate for the shortage of cognitive information. Conventionally, the covariates in the latent regression model are principal components extracted from background data. This operational method has several important disadvantages, such as the handling of missing data and…

There is a lack of research on the effects of outliers on the decisions about the number of factors to retain in an exploratory factor analysis, especially for outliers arising from unintended and unknowingly included subpopulations. The purpose of the present research was to investigate how outliers from an unintended and unknowingly included…

CEFA 3.02(Browne, Cudeck, Tateneni, & Mels, 2008) is a factor analysis computer program designed to perform exploratory factor analysis. It provides the main properties that are needed for exploratory factor analysis, namely a variety of factoring methods employing eight different discrepancy functions to be minimized to yield initial…

When conducting an exploratory factor analysis, the decision regarding the number of factors to retain following factor extraction is one that the researcher should consider very carefully, as the decision can have a dramatic effect on results. Although there are numerous strategies that can and should be utilized when making this decision,…

An alternative to the PROMAX exploratory method is presented for constructing a target matrix in Procrustean rotation in factor analysis. A technique is proposed based on vector majorization. The approach is illustrated with several standard numerical examples. (SLD)

Data reduction techniques seek to combine variables that account for patterns of variation in observed dependent variables in such a way that a simpler model is available for analysis. Factor analysis is a data reduction technique that attempts to model or explain a set of variables in terms of their associations. To understand why this technique…

A "doubly-centered" raw data matrix is one for which both columns and rows have both unit variance and means equal to zero. The factor scores from one analysis are the same as factor pattern coefficients from the other analysis except for a variance adjustment. This study explored an extension of the reciprocity principle which may have…

A method is proposed for the evaluation of the degree to which trait measures show stability across diverse methods of measurement. The technique is illustrated using multitrait-multimethod matrices from personality assessment, which yield trait-specific factors. (Author/BJG)

Exploratory factor analysis (EFA) is a frequently used multivariate analysis technique in statistics. Jennrich and Sampson (1966) solved a significant EFA factor loading matrix rotation problem by deriving the direct Quartimin rotation. Jennrich was also the first to develop standard errors for rotated solutions, although these have still not made…

Factor and cluster analyses are distinctly different multivariate procedures with different goals. However, when used in a complementary fashion, each set of methods can be used to enhance the interpretation of results found in the other set of methods. Simple examples illustrating the joint use of the methods are provided. (Author)

A modification of Horn's parallel analysis is introduced that is based on the Monte Carlo simulation of the null distributions of the eigenvalues generated from a population correlation identity matrix. This modification reduces the tendency of the parallel analysis procedure to overextract or to extract poorly defined factors. (SLD)

New ways of using factor analysis in research designs are suggested in this paper that would allow research to move in new directions that are being suggested for educational technology. A brief simplified overview of factor-analytic techniques is given, followed by a description of some recent developments in factor-analytic techniques which make…

The stability of psychometric "g," the general factor of intelligence, is investigated in simulated correlation matrices and in typical empirical data from a large battery of mental tests. "G" is robust and almost invariant across methods of analysis. A reasonable strategy for estimating "g" is suggested. (SLD)