Reliability of the 16PF questionnaire for security guard applicants

The Sixteen Personality Factor Questionnaire (16PF) was administered to a group of security guard applicants to determine its retest reliability after a moderate (9-month) interval. All of the Pearson correlations for specific test scales were lower than the reliabilities reported by the test's authors. These data raise questions as to the usefulness of the 16PF for the prediction of security guard behavior.     

An item factor analysis and item response theory-based revision of the Everyday Discrimination Scale

The Everyday Discrimination Scale (EDS), a widely used measure of daily perceived discrimination, is purported to be unidimensional, to function well among African Americans, and to have adequate construct validity. Two separate studies and data sources were used to examine and cross-validate the psychometric properties of the EDS. In Study 1, an exploratory factor analysis was conducted on a sample of African American law students (N = 589), providing strong evidence of local dependence, or nuisance multidimensionality within the EDS. In Study 2, a separate nationally representative community sample (N = 3,527) was used to model the identified local dependence in an item factor analysis (i.e., bifactor model). Next, item response theory (IRT) calibrations were conducted to obtain item parameters. A five-item, revised-EDS was then tested for gender differential item functioning (in an IRT framework). Based on these analyses, a summed score to IRT-scaled score translation table is provided for the revised-EDS. Our results indicate that the revised-EDS is unidimensional, with minimal differential item functioning, and retains predictive validity consistent with the original scale.     

An item and factor analysis of the FSS(III)

In view of the apparent need for an anxiety scale specifically for South African Indians, this study examines the characteristics of one such group on a stimulus-oriented measure of anxiety. The 73-item Fear Survey Schedule III (FSS) was administered to a representative sample of Natal Indians.Results suggest that this scale has good construct validity and internal consistency for the Ss. Item analyses indicate that stimuli associated with ‘tissue damage’ or ‘interpersonal’ situations are most anxiety-provoking and also correlate highest with test score remainders. A factor analysis reveals three dimensions of situational anxiety for South African Indians: ‘physical danger’, ‘interpersonal situations’ and ‘animals’. These findings support the contention that situational trait anxiety is a multi-dimensional phenomenon.     

Cross-cultural second order factor structures of the 16PF

Cross-cultural personality research has generated a great amount of data on individual difference patterns in diverse cultures. One of the major instruments used in this research has been Cattell's 16PF. A major question in this research is whether the underlying personality structure is equivalent for different cultures. The present study evaluated the second order factor structure of the 16PF in 101 subjects of European ancestry and 117 subjects of Japanese ancestry. The factor structure for the Japanese was significantly different from that of the caucasian group. The caucasian results did not differ from those reported by Cattell and his associates. The implications of these results for personality theory and for cross-cultural evaluation were briefly discussed.     

An empirical investigation of the influence of social desirability on the factor structure of the Chinese 16PF

This study examined whether social desirability affects the factor structure of the Chinese 16PF. Participants were 4645 Chinese first-year undergraduate and graduate students who completed the Chinese 16PF as part of a mandatory psychological assessment. Based on students’ score on the Impression Management scale (Paulhus, 1998), two groups were formed: (a) the high socially desirable responding group, consisting of students whose IM scores fell within the upper 20% of the distribution, and (b) the low socially desirable responding group, consisting of students whose IM scores fell within the bottom 25% of the distribution. A series of exploratory and confirmatory factor analyses indicated that the factor pattern and factor loadings of the Chinese 16PF were invariant across these two groups.     

Random intercept item factor analysis

The common factor model assumes that the linear coefficients (intercepts and factor loadings) linking the observed variables to the latent factors are fixed coefficients (i.e., common for all participants). When the observed variables are participants' observed responses to stimuli, such as their responses to the items of a questionnaire, the assumption of common linear coefficients may be too restrictive. For instance, this may occur if participants consistently use the response scale idiosyncratically. To account for this phenomenon, the authors partially relax the fixed coefficients assumption by allowing the intercepts in the factor model to change across participants. The model is attractive when m factors are expected on the basis of substantive theory but m + 1 factors are needed in practice to adequately reproduce the data. Also, this model for single-level data can be fitted with conventional software for structural equation modeling. The authors demonstrate the use of this model with an empirical data set on optimism in which they compare it with competing models such as the bifactor and the correlated trait-correlated method minus 1 models.     

An item response theory/confirmatory factor analysis of the Autobiographical Memory Test

The Autobiographical Memory Test (AMT) is used to assess the degree of specificity of autobiographical memory. The AMT usually contains cue words of both positive and negative valence, but it is unclear whether these valences form separate factors or not. Accordingly, confirmatory factor analysis assessed whether the AMT measures one overall factor, or whether different cue types are related to different factors. Results were consistent across three datasets (N = 333, N = 405, and N = 336). A one-factor model fitted each dataset well, which suggests that responses to positive and negative cues are related to the one construct. In addition, item response theory analyses showed that the AMT is most precise for people who score low on memory specificity. Implications for using the AMT with high-functioning samples are discussed.     

An improved stochastic EM algorithm for large-scale full-information item factor analysis

In this paper, we explore the use of the stochastic EM algorithm (Celeux & Diebolt (1985) Computational Statistics Quarterly, 2, 73) for large-scale full-information item factor analysis. Innovations have been made on its implementation, including an adaptive-rejection-based Gibbs sampler for the stochastic E step, a proximal gradient descent algorithm for the optimization in the M step, and diagnostic procedures for determining the burn-in size and the stopping of the algorithm. These developments are based on the theoretical results of Nielsen (2000, Bernoulli, 6, 457), as well as advanced sampling and optimization techniques. The proposed algorithm is computationally efficient and virtually tuning-free, making it scalable to large-scale data with many latent traits (e.g. more than five latent traits) and easy to use for practitioners. Standard errors of parameter estimation are also obtained based on the missing-information identity (Louis, 1982, Journal of the Royal Statistical Society, Series B, 44, 226). The performance of the algorithm is evaluated through simulation studies and an application to the analysis of the IPIP-NEO personality inventory. Extensions of the proposed algorithm to other latent variable models are discussed.     

Obtaining 16 PF Scores from the MMPI,and MMPI Scores from the 16 PF

Recent statistical analyses of the relation of the MMPI surface traits to the source traits in the 16 P.F. were extended to (a) the calculation of beta weights for estimating MMPI scale scores from the 16 P.F. and (b) deriving the MMPI item composition in terms of 16 P.F. scores from the MMPI, and vice versa. It has been argued from the specific nature of surface and source traits that additional diagnostic insight can be gained from their comparison, a principle which has been designated as depth psychometry.     

Sustaining fantasies and the 16 PF

This study examined the relationships between the Sustaining Fantasy Questionnaire (SFQ) and the 16 PF for 63 college students. The questionnaire is a self-report measure of characteristic fantasies used to reduce negative affect and maintain self-esteem. High scores on the fantasy scales having to do with power and revenge, death and illness, withdrawal and protection, and restitution, and on the scales measuring negative affect and the inability to produce comforting images were all associated with 16 PF indications of psychological distress.     

A Comparison of the Psychometric Properties of the 16PF4 and 16PF5 Among Male Anglican Clergy

Cattell's latest version of the 16PF (16PF5) was completed by a random sample of 580 male Anglican clergy whose names and addresses were provided by the Church Commissioners' payroll. These data demonstrated the robustness and reliability of the new instrument for this specialist population compared to the poor psychometric qualities of the 16PF4 as judged by the same criteria.     

Exploratory factor analysis: its role in item analysis

The special characteristics of items-low reliability, confounds by minor, unwanted covariance, and the likelihood of a general factor-and better understanding of factor analysis means that the default procedure of many statistical packages (Little Jiffy) is no longer adequate for exploratory item factor analysis. It produces too many factors and precludes a general factor even when that means the factors extracted are nonreplicable. More appropriate procedures that reduce these problems are presented, along with how to select the sample, sample size required, and how to select items for scales. Proposed scales can be evaluated by their correlations with the factors; a new procedure for doing so eliminates the biased values produced by correlating them with either total or factor scores. The role of exploratory factor analysis relative to cluster analysis and confirmatory factor analysis is noted.     

Heritability of item responses on the Eysenck personality questionnaire

We report estimates of the heritabilities and common environment variances for the 90 items of the Eysenck Personality Questionnaire. Responses from 627 pairs of twins were analysed using the biometrical genetic analysis based on the threshold model described by Falconer. Many of the items revealed very substantial heritabilities. No less than 67/90 had heritabilities > 33%, 19 had > 50% and a few were even > 65%. Some of the useful implications of item heritabilities are discussed.     

Confirmatory factor analysis of the AEQ-A questionnaire in Finland

The Adolescent version of the Alcohol Expectancy Questionnaire (Brown et al., 1980) was administered to a male population sample in Finland (N=195; median age 18.5 years). Three issues were investigated: Did the items of each subscale measure single latent constructs? Was the AEQ-A better described by a single-factor model (e.g., global positive expectancy) or by a null model implying scale independence? Were alcohol expectancies related to drinking habits? Confirmatory factor analyses by PRELIS2 and LISREL8 indicated that single-construct models were appropriate only for the Enhanced sexuality and Increased arousal scales while several items were unrelated to the postulated latent constructs in the other five scales. Adequate fits were obtained for these scales only when unrelated items were removedand/or anlayses were based on nondichotomus scores derived from contentwise homogenous groups of items. Even when revised so that the each scale formally fitted a single latent construct, the resulting latent constructs were not well described by either the single-factor model or the null model. Expected social benefit in terms of the revised Enhanced or impeded social behavior scale was the most significant predictor of drinking frequency while quantity consumed per drinking occasion was significantly related to the Improved cognitive and motor abilities scale only.