Exploring the Sensitivity of Horn's Parallel Analysis to the Distributional Form of Random Data

Horn's parallel analysis (PA) is the method of consensus in the literature on empirical methods for deciding how many components/factors to retain. Different authors have proposed various implementations of PA. Horn's seminal 1965 article, a 1996 article by Thompson and Daniel, and a 2004 article by Hayton, Allen, and Scarpello all make assertions about the requisite distributional forms of the random data generated for use in PA. Readily available software is used to test whether the results of PA are sensitive to several distributional prescriptions in the literature regarding the rank, normality, mean, variance, and range of simulated data on a portion of the National Comorbidity Survey Replication (Pennell et al., 2004) by varying the distributions in each PA. The results of PA were found not to vary by distributional assumption. The conclusion is that PA may be reliably performed with the computationally simplest distributional assumptions about the simulated data.

[1]  Sanjay Mishra,et al.  Efficient theory development and factor retention criteria: Abandon the ‘eigenvalue greater than one’ criterion , 2008 .

[2]  Wayne F. Velicer,et al.  Construct Explication through Factor or Component Analysis: A Review and Evaluation of Alternative Procedures for Determining the Number of Factors or Components , 2000 .

[3]  B. Thompson,et al.  Factor Analytic Evidence for the Construct Validity of Scores: A Historical Overview and Some Guidelines , 1996 .

[4]  R. M. Durand,et al.  Assessing Sampling Variation Relative to Number-of-Factors Criteria , 1990 .

[5]  Stéphane Dray,et al.  On the number of principal components: A test of dimensionality based on measurements of similarity between matrices , 2008, Comput. Stat. Data Anal..

[6]  R. Cattell.  The Scree Test For The Number Of Factors. , 1966, Multivariate behavioral research.

[7]  M. Torres,et al.  The development and implementation of the National Comorbidity Survey Replication, the National Survey of American Life, and the National Latino and Asian American Survey , 2004, International journal of methods in psychiatric research.

[8]  M. Browne,et al.  Alternative Ways of Assessing Model Fit , 1992 .

[9]  L. Guttman.  Some necessary conditions for common-factor analysis , 1954 .

[10]  R. MacCallum,et al.  THE APPLICATION OF EXPLORATORY FACTOR ANALYSIS IN APPLIED PSYCHOLOGY: A CRITICAL REVIEW AND ANALYSIS , 1986 .

[11]  K B Keeling,et al.  A Regression Equation for Determining the Dimensionality of Data , 2000, Multivariate behavioral research.

[12]  R. Stewart Longman,et al.  Comparing Different Methods for Implementing Parallel Analysis: A Practical Index of Accuracy , 1993 .

[13]  Kristopher J Preacher,et al.  Repairing Tom Swift's Electric Factor Analysis Machine , 2003 .

[14]  John L. Horn,et al.  A robust five-factor structure of the 16PF : Strong evidence from independent rotation and confirmatory factorial invariance procedures , 1997 .

[15]  James C. Hayton,et al.  Factor Retention Decisions in Exploratory Factor Analysis: a Tutorial on Parallel Analysis , 2004 .

[16]  Donald A. Jackson.  STOPPING RULES IN PRINCIPAL COMPONENTS ANALYSIS: A COMPARISON OF HEURISTICAL AND STATISTICAL APPROACHES' , 1993 .

[17]  C. Lance,et al.  The Sources of Four Commonly Reported Cutoff Criteria , 2006 .

[18]  J. Tanguma.  Determining the Number of Factors To Retain. , 2000 .

[19]  Louis W. Glorfeld.  An Improvement on Horn's Parallel Analysis Methodology for Selecting the Correct Number of Factors to Retain , 1995 .

[20]  J. Horn,et al.  Cattell's Scree Test In Relation To Bartlett's Chi-Square Test And Other Observations On The Number Of Factors Problem. , 1979, Multivariate behavioral research.

[21]  A. Silverstein.  Comparison of Two Criteria for Determining the Number of Factors , 1977 .

[22]  J. H. Steiger.  Statistically based tests for the number of common factors , 1980 .

[23]  Donald A. Jackson,et al.  How many principal components? stopping rules for determining the number of non-trivial axes revisited , 2005, Comput. Stat. Data Anal..

[24]  S J Allen,et al.  Notes and Commentary: Regression Equations for the Latent Roots of Random Data Correlation Matrices with Unities on the Diagonal. , 1986, Multivariate behavioral research.

[25]  G J Lautenschlager,et al.  A Comparison of Alternatives to Conducting Monte Carlo Analyses for Determining Parallel Analysis Criteria. , 1989, Multivariate behavioral research.

[26]  R S Longman,et al.  A Regression Equation for the Parallel Analysis Criterion in Principal Components Analysis: Mean and 95th Percentile Eigenvalues. , 1989, Multivariate behavioral research.

[27]  Norman Cliff,et al.  The eigenvalues-greater-than-one rule and the reliability of components. , 1988 .

[28]  Y. Benjamini,et al.  Controlling the false discovery rate: a practical and powerful approach to multiple testing , 1995 .

[29]  Y. Benjamini,et al.  THE CONTROL OF THE FALSE DISCOVERY RATE IN MULTIPLE TESTING UNDER DEPENDENCY , 2001 .

[30]  J. Horn.  A rationale and test for the number of factors in factor analysis , 1965, Psychometrika.

[31]  W. Velicer,et al.  Comparison of five rules for determining the number of components to retain. , 1986 .

[32]  H. Kaiser.  The Application of Electronic Computers to Factor Analysis , 1960 .

[33]  Lloyd G. Humphreys,et al.  Latent roots of random data correlation matrices with squared multiple correlations on the diagonal: A monte carlo study , 1976 .

[34]  W F Velicer,et al.  Component Analysis versus Common Factor Analysis: Some issues in Selecting an Appropriate Procedure. , 1990, Multivariate behavioral research.

[35]  S. Holm.  A Simple Sequentially Rejective Multiple Test Procedure , 1979 .