Taxometrics in Psychopathology Research: An Introduction to Some of the Procedures and Related Methodological Issues.

This article introduces a special section on the use of taxometrics to examine the categorical versus the dimensional structure of various forms of psychopathology. Paving the way into the special section, this introduction briefly describes 3 taxometric methods--mean above minus below a sliding cut (MAMBAC), maximum covariation (MAXCOV), and maximum eigenvalue (MAXEIG)--and discusses possible threats to statistical conclusion validity that often emerge when such techniques are applied in psychopathology research. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A comparison of parametric and non-parametric analyses of opinion data.

Questionnaire item responses were analyzed by testing the significance of the differences of percents in response categories, using a non-parametric test, and by testing the group differences in mean item scores, based on weights assigned the responses, using a critical ratio test. The two approaches gave equivalent results in almost all cases. Item mean scores correlated with percent-in-category generally .90 or higher. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Taxometric analyses of borderline personality features in a large-scale male and female offender sample.

Few studies to date have examined the extent to which borderline personality features are best construed as representing an underlying dimension or a discrete class or taxon. The authors conducted taxometric analyses using a large-scale sample of male (n = 787) and female (n = 368) prison inmates who had completed the Personality Assessment Inventory (L. C. Morey, 2007). Analyses based on the 4 subscales of the Borderline Features Scale offered compelling support for a dimensional structure in both the full sample and the female subsample--even after controlling for the potentially confounding effects of negative response distortion. Theoretical and pragmatic implications of these findings are reviewed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Relation between teachers' early expectations and students' later perceived competence in physical education classes: Autonomy-supportive climate as a moderator.

The purpose of this study was to explore whether, in naturalistic physical education classes, the relation between teachers' early expectations and students' later perceived competence was moderated by the extent to which the motivational climate created by the teachers was autonomy supportive. Using a 1-year longitudinal design, data were obtained from 421 students and 22 teachers from 10 French junior high schools. Multilevel analyses revealed that (a) teachers' early expectations were related to students' later perceived competence, particularly when these expectations were positive, and (b) this relation was stronger when the classroom motivational climate was low in autonomy support. Implications for future research and educational practices are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The latent structure of dietary restraint, body dissatisfaction, and drive for thinness: A series of taxometric analyses.

Although the latent structure of various eating disorders has been explored in previous studies, no published studies have examined the latent structure of theoretically relevant variables that have been shown to cut across eating disorder diagnoses. The current study examined 3 such variables (dietary restraint, body dissatisfaction, and drive for thinness) among undergraduate women using the taxometric method. The 5 items from the Eating Disorders Examination Questionnaire's Dietary Restraint subscale were used as dietary restraint indicators, whereas items from the Eating Disorders Inventory Body Dissatisfaction and Drive for Thinness subscales were used as indicators of body dissatisfaction and drive for thinness, respectively. As hypothesized, MAXCOV (maximum covariance) and MAMBAC (mean above minus below a cut) analyses suggested that all 3 variables are dimensional; therefore, individuals with high levels of reported dietary restraint, body dissatisfaction, and drive for thinness appear to differ in degree, but not in kind, from those with lower levels. Implications for prevention, assessment, classification, and treatment are discussed. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

The development of object categorization in young children: Hierarchical inclusiveness, age, perceptual attribute, and group versus individual analyses.

Multiple levels of category inclusiveness in 4 object domains (animals, vehicles, fruit, and furniture) were examined using a sequential touching procedure and assessed in both individual and group analyses in eighty 12-, 18-, 24-, and 30-month-olds. The roles of stimulus discriminability and child motor development, fatigue, and actions were also investigated. More inclusive levels of categorization systematically emerged before less inclusive levels, and a consistent advantage for categorizing high versus low perceptual contrasts was found. Group and individual analyses generally converged, but individual analyses added information about child categorization over group analyses. The development of object categorization in young children is discussed in light of efficiency of processing and similarity–differentiation theories. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Effects of contextual similarity and target-repetition proportion on negative priming in RT distributional analyses.

Participants' reaction time (RT) data in a prime-probe flanker task (e.g., ABA–CAC) were analyzed in terms of the characteristics of RT distribution to examine possible mechanisms that produce negative priming. When the prime and probe were presented in the same context and the proportion of repetition-target trials (TRP) was 0.33, negative priming increased as a function of RT bins, supporting the episodic retrieval account (Neill, 1997). Manipulations that discourage the use of episodic retrieval (i.e., switching context between prime and probe or 0.00 TRP) eliminated the increase in negative priming across RT bins, even though the overall effect remained significant. These data support a dual-mechanism account in which, depending on task demands, both selective inhibition and episodic retrieval can be involved in producing negative priming. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Social-cognitive determinants of physical activity: The influence of social support, self-efficacy, outcome expectations, and self-regulation among participants in a church-based health promotion study.

A social-cognitive model of physical activity was tested, using structural equation analysis of data from 999 adults (21% African American; 66% female; 38% inactive) recruited from 14 southwestern Virginia churches participating in the baseline phase of a health promotion study. Within the model, age, race, social support, self-efficacy, and self-regulation contributed to participants' physical activity levels, but outcome expectations did not. Of the social-cognitive variables, self-regulation exerted the strongest effect on physical activity. Independent of self-regulation, self-efficacy had little effect. Social support influenced physical activity as a direct precursor to self-efficacy and self-regulation. The model provided a good fit to the data and explained 46% of the variance in physical activity among the diverse group of adults. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The production and perception of long calls by cotton-top tamarins (Saguinus oedipus): Acoustic analyses and playback experiments.

Examined the cotton-top tamarin's production and perception of their combination long call (CLC). A series of acoustic analyses designed to determine the kind of information encoded in the CLC was conducted. Using factorial ANOVA and multiple discriminant analyses, identity information encoded in the CLC was explored: individual, sex, and social group. Exemplars could be reliably assigned to these 3 functional classes on the basis of a suite of spectrotemporal features. Second, a series of habituation–dishabituation playback experiments tested whether tamarins attend to the encoded information about individual identity. Tamarins were habituated to a series of calls from 1 tamarin and then played back a test call from a novel tamarin; both opposite- and same-sex pairings were tested. Results showed that tamarins dishabituated when caller identity changed but transferred habituation when caller identity was held constant and a new exemplar was played. Follow-up playback experiments revealed an asymmetry between the acoustic analyses of individual identity and the tamarins' capacity to discriminate among vocal signatures. Whereas all colony members have distinctive vocal signatures, not all tamarins were equally discriminable based on the habituation–dishabituation paradigm. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Screening for disruptive behavior syndromes in children: The application of latent class analyses and implications for prevention programs.

The predictive accuracy of classifying children at risk for disruptive disorders through latent class analyses (LCA) was evaluated. Child Behavior Checklist/4-18 (T. M. Achenbach, 1991) items, reflecting symptoms of Diagnostic and Statistical Manual of Mental Disorders (4th ed., American Psychiatric Association, 1994) defined disruptive disorders, alone and in combination with other child and familial risk factors, were used to predict children's risk for disruptive disorder. Predictive accuracy reached a positive predictive value of 69%. Children incorrectly classified (false positive and false negative) were compared with correctly classified children (true positive and true negative) on risk factors in the family context to test whether the screening procedure could be improved through a multiple-gating procedure. The differences in familial context factors between these children were limited, and no clear indications were found on how to use familial context factors to improve the screening procedure after the initial classification by LCA. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Confirmatory factor analyses of posttraumatic stress symptoms in deployed and nondeployed veterans of the Gulf War.

Confirmatory factor analysis was used to compare 6 models of posttraumatic stress disorder (PTSD) symptoms, ranging from 1 to 4 factors, in a sample of 3,695 deployed Gulf War veterans (N = 1,896) and nondeployed controls (N = 1,799). The 4 correlated factors-intrusions, avoidance, hyperarousal, and dysphoria-provided the best fit. The dysphoria factor combined traditional markers of numbing and hyperarousal. Model superiority was cross-validated in multiple subsamples, including a subset of deployed participants who were exposed to traumatic combat stressors. Moreover, convergent and discriminant validity correlations suggested that intrusions may be relatively specific to PTSD, whereas dysphoria may represent a nonspecific component of many disorders. Results are discussed in the context of hierarchical models of anxiety and depression. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Further assessment of the HEXACO Personality Inventory: Two new facet scales and an observer report form.

The HEXACO Personality Inventory (HEXACO-PI) operationalizes the six factors obtained from lexical studies of personality structure in several languages. In this study, psychometric properties of the HEXACO-PI were assessed using a community adult sample and also using observer reports, thereby extending the previous investigation relying only on self-reports from a college student sample. In addition to examining the original 24 HEXACO-PI facet scales, the authors also examined two new facet scales--Altruism versus Antagonism and Negative Self-Evaluation--that assess constructs located interstitially among the factors of the HEXACO space. The HEXACO-PI again showed favorable psychometric properties in terms of reliability and factor structure and also showed high levels of self/observer agreement. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Assumptions of cross-level measurement and structural invariance in the analysis of multilevel data: Problems and solutions.

This article demonstrates assumptions of invariance that researchers often implicitly make when analyzing multilevel data. The first set of assumptions is measurement-based and corresponds to the fact that researchers often conduct single-level exploratory and confirmatory factor analyses, and reliability analyses, with multilevel data. The second assumption, that of structural invariance, is engineered into the common multilevel random coefficient model, in that such analyses impose structural invariance across multiple levels of analysis when lower-level relationships represent both between- and within-groups effects. The nature of these assumptions, and ways to address their tenability, are explored from a conceptual standpoint. Then an empirical example of these assumptions and ways to address them is provided. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

More Information From Fewer Questions: The Factor Structure and Item Properties of the Original and Brief Fear of Negative Evaluation Scale.

Statistical methods designed for categorical data were used to perform confirmatory factor analyses and item response theory (IRT) analyses of the Fear of Negative Evaluation scale (FNE; D. Watson & R. Friend, 1969) and the Brief FNE (BFNE; M. R. Leary, 1983). Results suggested that a 2-factor model fit the data better for both the FNE and the BFNE, although the evidence was less strong for the FNE. The IRT analyses indicated that although both measures had items with good discrimination, the FNE items discriminated only at lower levels of the underlying construct, whereas the BFNE items discriminated across a wider range. Convergent validity analyses indicated that the straightforwardly-worded items on each scale had significantly stronger relationships with theoretically related measures than did the reverse-worded items. On the basis of all analyses, usage of the straightforwardly-worded BFNE factor is recommended for the assessment of fear of negative evaluation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Short and long views of integrative data analysis: Comments on contributions to the special issue.

The author comments on the potential of integrative data analysis (IDA) as a new methodological activity and on some of the topics that were discussed in the 5 articles in this special issue. One topic is the extent to which IDA will be used to provide conclusive summaries regarding the strength of evidence for well-specified questions versus to provide new information that goes beyond the simple sum of individual studies. Another is the meaning of variances of effects that are observed over studies and sample strata. A 3rd is the potential to enhance understanding of construct validity by fitting measurement models described in the special issue. The author concludes by recommending critical examination of model-based inferences from IDA through sensitivity analyses and by noting that IDA can promote collaboration and networks that yield data that are more amenable to integrated analyses in the future. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The search for dimensional structure differences between normality and abnormality: A statistical review of published data on personality and psychopathology.

A statistical review of published data for 37 personality and psychopathology inventories was conducted to determine whether there are dimensional structure differences between clinical and nonclinical respondents. Correlation and factor-loading matrices from multiscale inventories and from specialized measures were tested for structural invariance across populations. There was relatively consistent evidence for high levels of similarity between normal and abnormal populations both in the number of factors that exist in the data matrices and in the factor patterns. The dimensional universes of normality and abnormality are apparently the same, at least according to data derived from contemporary assessment instruments. Categorical-taxonic differences between clinical and nonclinical populations, which were not examined, may nevertheless exist within contexts of dimensional structure similarity. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

Inference in regression models of heavily skewed alcohol use data: A comparison of ordinary least squares, generalized linear models, and bootstrap resampling.

Analysis of alcohol use data and other low base rate risk behaviors using ordinary least squares regression models can be problematic. This article presents 2 alternative statistical approaches, generalized linear models and bootstrapping, that may be more appropriate for such data. First, the basic theory behind the approaches is presented. Then, using a data set of alcohol use behaviors and consequences, results based on these approaches are contrasted with the results from ordinary least squares regression. The less traditional approaches consistently demonstrated better fit with model assumptions, as demonstrated by graphical analysis of residuals, and identified more significant variables potentially resulting in theoretically different interpretations of the models of alcohol use. In conclusion, these models show significant promise for furthering the understanding of alcohol-related behaviors. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Case matching and the reduction of selection bias in quasi-experiments: The relative importance of pretest measures of outcome, of unreliable measurement, and of mode of data analysis.

In this article, we note the many ontological, epistemological, and methodological similarities between how Campbell and Rubin conceptualize causation. We then explore 3 differences in their written emphases about individual case matching in observational studies. We contend that (a) Campbell places greater emphasis than Rubin on the special role of pretest measures of outcome among matching variables; (b) Campbell is more explicitly concerned with unreliability in the covariates; and (c) for analyzing the outcome, only Rubin emphasizes the advantages of using propensity score over regression methods. To explore how well these 3 factors reduce bias, we reanalyze and review within-study comparisons that contrast experimental and statistically adjusted nonexperimental causal estimates from studies with the same target population and treatment content. In this context, the choice of covariates counts most for reducing selection bias, and the pretest usually plays a special role relative to all the other covariates considered singly. Unreliability in the covariates also influences bias reduction but by less. Furthermore, propensity score and regression methods produce comparable degrees of bias reduction, though these within-study comparisons may not have met the theoretically specified conditions most likely to produce differences due to analytic method. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

On the additive effects of stimulus quality and word frequency in lexical decision: Evidence for opposing interactive influences revealed by RT distributional analyses.

The joint effects of stimulus quality and word frequency in lexical decision were examined in 4 experiments as a function of nonword type (legal nonwords, e.g., BRONE, vs. pseudohomophones, e.g., BRANE). When familiarity was a viable dimension for word-nonword discrimination, as when legal nonwords were used, additive effects of stimulus quality and word frequency were observed in both means and distributional characteristics of the response-time distributions. In contrast, when the utility of familiarity was undermined by using pseudohomophones, additivity was observed in the means but not in distributional characteristics. Specifically, opposing interactive effects in the underlying distribution were observed, producing apparent additivity in means. These findings are consistent with the suggestion that, when familiarity is deemphasized in lexical decision, cascaded processing between letter and word levels is in play, whereas, when familiarity is a viable dimension for word-nonword discrimination, processing is discrete. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

What are the causes of reduced fit in scaling and clustering studies of semantic proximity data, and how else to measure them: A comment on Storms et al. (2003).

G. Storms, T. Dirikx, J. Saerens, S. Verstraeten, and P. P. De Deyn (2003) noted that the goodness-of-fit indices for scaling and clustering solutions of proximity data from populations with hypothesized semantic deficits tend to be reduced in comparison with control participants, and that this precludes an unambiguous interpretation of such data. However, this effect is not necessarily as inconsistent with the proposal of semantic degradation in these groups, or as consistent with explanations in terms of access or attentional problems, as is suggested by G. Storms et al. Also, although performance on word fluency tasks is certainly constrained by the ability to access stored information, there are ways in which this confounding influence may be controlled for in the study of semantic deficits. (PsycINFO Database Record (c) 2010 APA, all rights reserved)