Comparing meta-analytic moderator estimation techniques under realistic conditions.

One of the most problematic issues in contemporary meta-analysis is the estimation and interpretation of moderating effects. Monte Carlo analyses are developed in this article that compare bivariate correlations, ordinary least squares and weighted least squares (WLS) multiple regression, and hierarchical subgroup (HS) analysis for assessing the influence of continuous moderators under conditions of multicollinearity and skewed distribution of study sample sizes (heteroscedasticity). The results show that only WLS is largely unaffected by multicollinearity and heteroscedasticity, whereas the other techniques are substantially weakened. Of note, HS, one of the most popular methods, typically provides the most inaccurate results, whereas WLS, one of the least popular methods, typically provides the most accurate results. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Latent structure analysis of DSM-IV borderline personality disorder criteria

The aim of this study was to evaluate the structure of DSM-IV borderline personality disorder (BPD) criteria. The study group consisted of 564 consecutively admitted inpatients and outpatients. BPD criteria discriminatory power was tested by using corrected item-to-total and item-to-diagnosis correlations. Weighted least-squares (WLS) confirmatory factor analysis (CFA) was used to assess the fit of DSM-IV BPD unidimensional model. The categorical model of BPD was tested by exploratory latent class analysis (LCA). Item analysis suggested a hierarchy in BPD criteria discriminatory power, even if with different rank order with respect to the DSM-IV model. CFA showed a unifactorial structure with congeneric items as the best fitting model for DSM-IV BPD criteria (chi2 = 18.89, df= 27, P > .87). LCA showed evidence for three latent classes; heterogeneity was observed only among subjects falling below DSM-IV diagnostic threshold for BPD. These results support the categorical model of BPD, even if with several differences with respect to DSM-IV.     

The continuity principle in psychological research: An introduction to robust statistics.

Examines the importance of robust statistics in psychological research and suggests that the classical estimates of means, variances, and correlations are sensitive to small departures from the normal curve. Statisticians have urged caution in the use of classical statistics and have proposed a variety of alternatives that are robust with respect to departures from normality. Common sources of nonnormality in psychological data cleaning and robust estimation are examined. Robust estimation using M-estimators is discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Gain in efficiency from using generalized least squares in the Haseman-Elston test

Techniques that test for linkage between a marker and a trait locus based on the regression methods proposed by Haseman and Elston [1972] involve testing a null hypothesis of no linkage by examination of the regression coefficient. Modified Haseman-Elston methods accomplish this using ordinary least squares (OLS), weighted least squares (WLS), in which weights are reciprocals of estimated variances, and generalized estimating equations (GEE). Methods implementing the WLS and GEE currently use a diagonal covariance matrix, thus incorrectly treating the squared trait differences of two sib pairs within a family as uncorrelated. Correctly specifying the correlations between sib pairs in a family yields the best linear unbiased estimator of the regression coefficient [Scheffe, 1959]. This estimator will be referred to as the generalized least squares (GLS) estimator. We determined the null variance of the GLS estimator and the null variance of the WLS/OLS estimator. The correct null variance of the WLS/OLS estimate of the Haseman-Elston (H-E) regression coefficient may be either larger or smaller than the variance of the WLS/OLS estimate calculated assuming that the squared sib-pair differences are uncorrelated. For a fully informative marker locus, the gain in efficiency using GLS rather than WLS/OLS under the null hypothesis is approximately 11% in a large multifamily study with three siblings per family and 25% for families with four siblings each.     

Dimensionality assessment of ordered polytomous items with parallel analysis.

Parallel analysis (PA) is an often-recommended approach for assessment of the dimensionality of a variable set. PA is known in different variants, which may yield different dimensionality indications. In this article, the authors considered the most appropriate PA procedure to assess the number of common factors underlying ordered polytomously scored variables. They proposed minimum rank factor analysis (MRFA) as an extraction method, rather than the currently applied principal component analysis (PCA) and principal axes factoring. A simulation study, based on data with major and minor factors, showed that all procedures consistently point at the number of major common factors. A polychoric-based PA slightly outperformed a Pearson-based PA, but convergence problems may hamper its empirical application. In empirical practice, PA-MRFA with a 95% threshold based on polychoric correlations or, in case of nonconvergence, Pearson correlations with mean thresholds appear to be a good choice for identification of the number of common factors. PA-MRFA is a common-factor-based method and performed best in the simulation experiment. PA based on PCA with a 95% threshold is second best, as this method showed good performances in the empirically relevant conditions of the simulation experiment. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

Modified parallel analysis: A procedure for examining the latent dimensionality of dichotomously scored item responses.

A procedure, termed modified parallel analysis, is proposed for determining when violations of the assumption of unidimensionality in item response theories are too severe to allow satisfactory parameter estimation. Several Monte Carlo simulation experiments show that the procedure can detect violations of unidimensionality that interfere with parameter estimation. An example of the use of modified parallel analysis is presented in which the comparability of English and French versions of the Otis-Lennon School Abilities Test was examined using data from 1,239 junior and senior high school students. (19 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Effect of violation of normality on the t test of the correlation coefficient.

Performed simulations to study the effects of violations of the normality assumption on the t test of the Pearson product-moment correlation coefficient. The test was robust as long as the variables were independent, even with violations in combined distributions. Large effects for violations of normality were found when the variables were not independent, even though the population correlation was zero. (18 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Temporal patterns of variable relationships in person-oriented research: Longitudinal models of configural frequency analysis.

This article reviews the premises of configural frequency analysis (CFA), including methods of choosing significance tests and base models, as well as protecting α, and discusses why CFA is a useful approach when conducting longitudinal person-oriented research. CFA operates at the manifest variable level. Longitudinal CFA seeks to identify those temporal patterns that stand out as more frequent (CFA types) or less frequent (CFA antitypes) than expected with reference to a base model. A base model that has been used frequently in CFA applications, prediction CFA, and a new base model, auto-association CFA, are discussed for analysis of cross-classifications of longitudinal data. The former base model takes the associations among predictors and among criteria into account. The latter takes the auto-associations among repeatedly observed variables into account. Application examples of each are given using data from a longitudinal study of domestic violence. It is demonstrated that CFA results are not redundant with results from log-linear modeling or multinomial regression and that, of these approaches, CFA shows particular utility when conducting person-oriented research. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Understanding psychopathy through an evaluation of interpersonal behavior: Testing the factor structure of the interpersonal measure of psychopathy in a large sample of jail detainees.

Interpersonal characteristics are core features of the psychopathy construct which have a unique pattern of correlations with a variety of external correlates. To improve the assessment of interpersonal traits, the current study evaluated the internal structure of the Interpersonal Measure of Psychopathy (IM–P) through exploratory and confirmatory factor analyses (CFA) in a large sample of jail inmates. A 17-item, 3-factor (Dominance, Grandiosity, and Boundary Violations) structure evidenced good fit in European American inmates. A second CFA demonstrated good fit for this structure in a sample of African American inmates. Moreover, a multigroup CFA indicated structural invariance between European and African American inmates. External validity was tested and demonstrated through positive correlations between IM–P factor scores and Psychopathy Checklist—Revised total and facet scores (R. D. Hare, 2003) and antisocial personality disorder symptoms and diagnoses. Modest correlations between Grandiosity scores and scores on the Shipley Institute of Living Scale—Revised (R. A. Zachary, 1994) were also observed. Finally, a step-down hierarchical regression was conducted to test for racial bias of the IM–P factor scores in relation to external correlates. Little evidence was found for slope bias, but there was evidence of intercept bias for some analyses. Implications and advantages of assessing psychopathy through a comprehensive evaluation of interpersonal traits are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Evaluation of laboratory methods for the study of driver behavior: Relations between simulator and street performance.

Road performance data on 304 taxi drivers were obtained by pairs of trained observers using behavioral checklists. Drivers did not know they were being observed. 66% of the drivers then agreed to participate in the laboratory study, which involved performance on 2 different driving simulators and on 4 perceptual–motor tests. Officially recorded accidents and violations over a 5-yr period were obtained for each S for comparison with performance data. Results show that few of the scores from the simulators or tests were significantly correlated with road performance; however, a number of significant relations were found between perceptual–motor test performance and simulator performance. Although these correlations were not high, they tended to be more significant than those between performance on the 2 simulators. Age was negatively correlated with simulator performance. Relations between all performance measures and officially recorded accident and violation data were low. Some significant predictors of certain classes of violations were achieved from road performance measures obtained in the study. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Confidence intervals for gamma-family measures of ordinal association.

[Correction Notice: An erratum for this article was reported in Vol 13(1) of Psychological Methods (see record 2008-02525-006). The note corrects simulation results presented in the article concerning the performance of confidence intervals (CIs) for Spearman's rs. An error in the author's C++ code affected all simulation results for Spearman's rs (but none of the results for gamma-family indices).] This research focused on confidence intervals (CIs) for 10 measures of monotonic association between ordinal variables. Standard errors (SEs) were also reviewed because more than 1 formula was available per index. For 5 indices, an element of the formula used to compute an SE is given that is apparently new. CIs computed with different SEs were compared in simulations with small samples (N = 25, 50, 75, or 100) for variables with 4 or 5 categories. With N > 25, many CIs performed well. Performance was best for consistent CIs due to N. Cliff and colleagues (N. Cliff, 1996; N. Cliff & V. Charlin, 1991; J. D. Long & N. Cliff, 1997). CIs for Spearman's rank correlation were also examined: Parameter coverage was erratic and sometimes egregiously underestimated. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

An Alternative Perspective on von Winterfeldt et al.'s (1997) Test of Consequence Monotonicity.

D. von Winterfeldt, N.-K. Chung, R. D. Luce, and Y. Cho (see record 1997-03378-008) provided several tests for consequence monotonicity of choice or judgment, using certainty equivalents of gambles. The authors reaxiomatized consequence monotonicity in a probabilistic framework and reanalyzed von Winterfeldt et al.'s main experiment via a bootstrap method. Their application offers new insights into consequence monotonicity as well as into von Winterfeldt et al.'s 3 experimental paradigms: judged certainty equivalents (JCE), QUICKINDIFF, and parameter estimation by sequential testing (PEST). For QUICKINDIFF, the authors found no indication of violations of "random consequence monotonicity." This sharply contrasts the findings of von Winterfeldt et al., who concluded that axiom violations were the most pronounced under that procedure. The authors found potential evidence for violations in JCE and certainty equivalents derived from PEST. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

In defense of functional independence: Violations of assumptions underlying the process-dissociation procedure?

T. Curran and D. L. Hintzman (see record 1995-42725-001) claim to have shown that the independence assumption underlying the process-dissociation procedure (L. L. Jacoby, see record 1992-07943-001) is not justified. They argued that correlations between processes at the level of items can result in an underestimation of automatic processes large enough to produce artifactual dissociations between process estimates. In contrast, the authors show that the effects of extremely high correlations at the level of items are likely to be trivial, and not differential across conditions. Curran and Hintzman's dissociations probably reflect violations of boundary conditions for use of the process-dissociation procedure, rather than violations of independence. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Short forms of the Wechsler Memory Scale—Revised: Cross-validation and derivation of a two-subtest form.

J. L. Woodard and B. N. Axelrod (1995) and B. N. Axelrod, S. H. Putnam, J. L. Woodard, and K. M. Adams (1996) have presented formulas for estimating the Wechsler Memory Scale—Revised General Memory and Delayed Recall Indexes using the initial and delayed portions of only 3 subtests. The original work found nearly perfect estimates. The present study indicated excellent cross-validation for the original formulas with correlations of .99. Over 85% of the estimated scores were within 6 points of the actual score. Using estimates from only 2 subtests rather than 3, correlations were only slightly lower with 85% of the estimated scores within 10 points of the actual scores. Age, education, diagnosis, and IQ had no effects on the accuracy of these equations. Although the initial 3 test formulas are robust, the results suggest that using only 2 subtests results in higher estimation errors, which can be used when less accurate estimates are acceptable (such as in group research). (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Meta-Analytic Methods of Pooling Correlation Matrices for Structural Equation Modeling Under Different Patterns of Missing Data.

Three methods of synthesizing correlations for meta-analytic structural equation modeling (SEM) under different degrees and mechanisms of missingness were compared for the estimation of correlation and SEM parameters and goodness-of-fit indices by using Monte Carlo simulation techniques. A revised generalized least squares (GLS) method for synthesizing correlations, weighted-covariance GLS (W-COV GLS), was compared with univariate weighting with untransformed correlations (univariate r) and univariate weighting with Fisher's z-transformed correlations (univariate z). These 3 methods were crossed with listwise and pairwise deletion. Univariate z and W-COV GLS performed similarly, with W-COV GLS providing slightly better estimation of parameters and more correct model rejection rates. Missing not at random data produced high levels of relative bias in correlation and model parameter estimates and higher incorrect SEM model rejection rates. Pairwise deletion resulted in inflated standard errors for all synthesis methods and higher incorrect rejection rates for the SEM model with univariate weighting procedures. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

"Confidence intervals for gamma-family measures of ordinal association": Correction.

Reports an error in "Confidence intervals for gamma-family measures of ordinal association" by Carol M. Woods (Psychological Methods, 2007[Jun], Vol 12[2], 185-204). The note corrects simulation results presented in the article concerning the performance of confidence intervals (CIs) for Spearman's rs. An error in the author's C++ code affected all simulation results for Spearman's rs (but none of the results for gamma-family indices). (The following abstract of the original article appeared in record 2007-07830-005.) This research focused on confidence intervals (CIs) for 10 measures of monotonic association between ordinal variables. Standard errors (SEs) were also reviewed because more than 1 formula was available per index. For 5 indices, an element of the formula used to compute an SE is given that is apparently new. CIs computed with different SEs were compared in simulations with small samples (N = 25, 50, 75, or 100) for variables with 4 or 5 categories. With N > 25, many CIs performed well. Performance was best for consistent CIs due to N. Cliff and colleagues (N. Cliff, 1996; N. Cliff & V. Charlin, 1991; J. D. Long & N. Cliff, 1997). CIs for Spearman's rank correlation were also examined: Parameter coverage was erratic and sometimes egregiously underestimated. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Analysis of the multitrait-multimethod matrix by confirmatory factor analysis.

The multitrait–multimethod (MTMM) matrix permits examination of the convergent and discriminant validity of psychological measures. Estimation using confirmatory factor analysis (CFA), the predominant analytical technique, has often resulted in severe difficulties, such as out-of-range estimates and convergence problems. This article shows that an important special case of one of the more frequently advocated CFA models is not identified and is therefore not estimable. Because most MTMM data are likely to conform closely to this special case, resulting analyses suffer from empirical underidentification. Alternative CFA models are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A survey of client-therapist sexual involvement in Rhode Island as reported by subsequent treating therapists.

In this study, the authors surveyed all licensed mental health professionals in the state of Rhode Island and asked them if they had treated clients who had been sexually abused by a former therapist. Twenty-six percent of the respondents reported having treated victims of therapist sexual abuse. In addition, the treating therapists reported 120 incidents of other boundary violations. These data point to a dramatic difference between the actual occurrence of therapy boundary violations and the reporting of violations to state licensing boards. The nature of the violations that do occur and the impact on patient victims are also discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

O-GlcNAcylation of key nuclear and cytoskeletal proteins: reciprocity with O-phosphorylation and putative roles in protein multimerization

BACKGROUND: Registered mortality from cryptogenic fibrosing alveolitis (CFA) in England and Wales has increased substantially since the specific International Classification of Diseases code for CFA was introduced in 1979. However, since a significant proportion of deaths from CFA are misclassified as post inflammatory fibrosis (PIF), it is possible that the observed rise in CFA mortality is due to diagnostic transfer from this code. To investigate this, and to assess mortality trends in other countries, annual CFA and PIF mortality data from England and Wales, USA, Australia, Scotland, Canada, New Zealand, and Germany were analysed. METHODS: Crude annual mortality rates were calculated and rates standardised by Poisson regression to allow assessment of changes over time and comparison between countries, sexes, and age groups. The relative trends in mortality from CFA and PIF were assessed by calculating the annual ratio of CFA to PIF deaths. RESULTS: Men were more likely than women to die from both CFA and PIF in all countries. The highest standardised CFA mortality rate occurred in England and Wales, and the lowest in Germany. Since 1979 mortality from CFA has increased in England and Wales, Australia, Scotland and Canada, but there was no trend in CFA mortality in New Zealand or Germany. In the USA mortality from CFA was low and has fallen. Mortality from PIF increased in all countries except New Zealand and Germany, and the highest PIF mortality, together with the greatest increase over time, was seen in the USA. Changes over time in the annual ratio of CFA to PIF deaths in all countries were small, implying that diagnostic transfer is not a major cause of the increasing CFA mortality. CONCLUSIONS: Mortality from CFA continues to increase in England and Wales and in many other countries. Diagnostic transfer from PIF does not appear to be a major cause of this.