Do We Hold Males and Females to the Same Standard? A Measurement Invariance Study on the Psychopathy Checklist-Revised.

Psychopathy in females has been understudied. Extant data on gender comparisons using the predominant measure of assessment in clinical practice, the Psychopathy Checklist Revised (PCL-R), points to a potential lack of measurement invariance (MI). If indeed the instrument does not perform equally (well) in both genders, straightforward comparison of psychopathy scores in males and females is unwarranted. Using a sample of female and male forensic patients (N = 110 and N = 147 respectively), we formally tested for MI in a structural equation modeling framework. We found that the PCL-R in its current form does not attain full MI. Four items showed threshold-biases and particularly Factor 2 (the Social Deviance Factor) is gender biased. Based on our findings, it seems reasonable to expect that specific scoring adjustments might go a long way in bringing about more equivalent assessment of psychopathic features in men and women. Only then can we begin to meaningfully compare the genders on the prevalence, structure, and external correlates of psychopathy.

Nonlinear Indicator-Level Moderation in Latent Variable Models.

Linear, nonlinear, and nonparametric moderated latent variable models have been developed to investigate possible interaction effects between a latent variable and an external continuous moderator on the observed indicators in the latent variable model. Most moderation models have focused on moderators that vary across persons but not across the indicators (e.g., moderators like age and socioeconomic status). However, in many applications, the values of the moderator may vary both across persons and across indicators (e.g., moderators like response times and confidence ratings). Indicator-level moderation models are available for categorical moderators and linear interaction effects. However, these approaches require respectively categorization of the continuous moderator and the assumption of linearity of the interaction effect. In this article, parametric nonlinear and nonparametric indicator-level moderation methods are developed. In a simulation study, we demonstrate the viability of these methods. In addition, the methods are applied to a real data set pertaining to arithmetic ability.

A heteroscedastic hidden Markov mixture model for responses and categorized response times.

Various mixture modeling approaches have been proposed to identify within-subjects differences in the psychological processes underlying responses to psychometric tests. Although valuable, the existing mixture models are associated with at least one of the following three challenges: (1) A parametric distribution is assumed for the response times that-if violated-may bias the results; (2) the response processes are assumed to result in equal variances (homoscedasticity) in the response times, whereas some processes may produce more variability than others (heteroscedasticity); and (3) the different response processes are modeled as independent latent variables, whereas they may be related. Although each of these challenges has been addressed separately, in practice they may occur simultaneously. Therefore, we propose a heteroscedastic hidden Markov mixture model for responses and categorized response times that addresses all the challenges above in a single model. In a simulation study, we demonstrated that the model is associated with acceptable parameter recovery and acceptable resolution to distinguish between various special cases. In addition, the model was applied to the responses and response times of the WAIS-IV block design subtest, to demonstrate its use in practice.

Dependence of Gene-by-Environment Interactions (GxE) on Scaling: Comparing the Use of Sum Scores, Transformed Sum Scores and IRT Scores for the Phenotype in Tests of GxE.

Estimates of gene-environment interactions (GxE) in behavior genetic models depend on how a phenotype is scaled. Inappropriately scaled phenotypes result in biased estimates of GxE and can sometimes even suggest GxE in the direction opposite to its true direction. Previously proposed solutions are mathematically complex, computationally demanding and may prove impractical for the substantive researcher. We, therefore, evaluated two simple-to-use alternatives: (1) straightforward non-linear transformation of sum scores and (2) factor scores from an appropriate item response theory (IRT) model. Within Purcell's (2002) GxM framework, both alternatives provided less biased parameter estimates, and improved false and true positive rates than using a raw sum score. These approaches are, therefore, recommended over using raw sum scores in tests of GxE. Circumstances under which IRT factor scores versus transformed sum scores should be preferred are discussed.

Evidence for Gender-Dependent Genotype by Environment Interaction in Adult Depression.

Depression in adults is heritable with about 40 % of the phenotypic variance due to additive genetic effects and the remaining phenotypic variance due to unique (unshared) environmental effects. Common environmental effects shared by family members are rarely found in adults. One possible explanation for this finding is that there is an interaction between genes and the environment which may mask effects of the common environment. To test this hypothesis, we investigated genotype by environment interaction in a large sample of female and male adult twins aged 18-70 years. The anxious depression subscale of the Adult Self Report from the Achenbach System of Empirically Based Assessment (Achenbach and Rescorla in Manual for the ASEBA adult: forms and profiles, 2003) was completed by 13,022 twins who participate in longitudinal studies of the Netherlands Twin Register. In a single group analysis, we found genotype by unique environment interaction, but no genotype by common environment interaction. However, when conditioning on gender, we observed genotype by common environment interaction in men, with larger common environmental variance in men who are genetically less at risk to develop depression. Although the effect size of the interaction is characterized by large uncertainty, the results show that there is at least some variance due to the common environment in adult depression in men.

Hidden Markov Item Response Theory Models for Responses and Response Times.

Current approaches to model responses and response times to psychometric tests solely focus on between-subject differences in speed and ability. Within subjects, speed and ability are assumed to be constants. Violations of this assumption are generally absorbed in the residual of the model. As a result, within-subject departures from the between-subject speed and ability level remain undetected. These departures may be of interest to the researcher as they reflect differences in the response processes adopted on the items of a test. In this article, we propose a dynamic approach for responses and response times based on hidden Markov modeling to account for within-subject differences in responses and response times. A simulation study is conducted to demonstrate acceptable parameter recovery and acceptable performance of various fit indices in distinguishing between different models. In addition, both a confirmatory and an exploratory application are presented to demonstrate the practical value of the modeling approach.

When Middle Really Means "Top" or "Bottom": An Analysis of the 16PF5 Using Bock's Nominal Response Model.

When self-report items with a Likert-type scale include a middle response option (e.g., Unsure, Neither agree nor disagree, or ?), this middle option is assumed to measure a level of the trait intermediate between the high and low response categories. In this study, we tested this assumption in the 16 Personality Factor Questionnaire, Version 5 (16PF5) by fitting Bock's nominal response model in the U.S. and UK standardization samples of the 16PF5. We found that in many cases, the middle option was indicative of higher levels of the latent trait than the ostensibly highest response option. In certain other cases, it was indicative of lower levels of the latent trait than the ostensibly lowest response option. This undermines the use of a simple successive integer scoring scheme where responses in adjacent response categories are assigned scores of 0, 1, and 2. Recommendations for alternative scoring schemes are provided. Results also suggested that certain personality traits, especially neurotic traits, are associated with a tendency toward selecting the middle option.

Analysis of Behavioral and Emotional Problems in Children Highlights the Role of Genotype × Environment Interaction.

This study tested for Genotype × Environment (G × E) interaction on behavioral and emotional problems in children using new methods that do not require identification of candidate genes or environments, can distinguish between interaction with shared and unique environment, and are insensitive to scale effects. Parental ratings of problem behavior from 14,755 twin pairs (5.3 years, SD = 0.22) indicated G × E interaction on emotional liability, social isolation, aggression, attention problems, dependency, anxiety, and physical coordination. Environmental influences increased in children who were genetically more predisposed to problem behavior, with ~20% of the variance due to G × E interaction (8% for anxiety to 37% for attention problems). Ignoring G × E interaction does not greatly bias heritability estimates, but it does offer a comprehensive model of the etiology for childhood problems.

A Bivariate Generalized Linear Item Response Theory Modeling Framework to the Analysis of Responses and Response Times.

A generalized linear modeling framework to the analysis of responses and response times is outlined. In this framework, referred to as bivariate generalized linear item response theory (B-GLIRT), separate generalized linear measurement models are specified for the responses and the response times that are subsequently linked by cross-relations. The cross-relations can take various forms. Here, we focus on cross-relations with a linear or interaction term for ability tests, and cross-relations with a curvilinear term for personality tests. In addition, we discuss how popular existing models from the psychometric literature are special cases in the B-GLIRT framework depending on restrictions in the cross-relation. This allows us to compare existing models conceptually and empirically. We discuss various extensions of the traditional models motivated by practical problems. We also illustrate the applicability of our approach using various real data examples, including data on personality and cognitive ability.

Testing systematic genotype by environment interactions using item level data.

Investigating genotype by environment interactions (GxE) is generally considered challenging due to the scale dependency of the interaction effect. The present paper illustrates the problems associated with testing for GxEs on summed item scores within the well-known ACE model. That is, it is shown how genuine GxEs may be masked and how spurious interactions can arise from scaling issues in the data. A solution is proposed which explicitly distinguishes between a measurement model for the ordinal item responses and a biometric model in which the GxE effects are investigated. The new approach is studied in a simulation study using both a scenario in which the measurement instrument suffers from mild scaling problems and a scenario in which the measurement instrument suffers from severe scaling problems. Results indicate that the severity of the scale problems affects the power to detect GxE, but it rarely results in false positives. We illustrate the new approach on a real dataset concerning affect.