Psychometric Modeling of response speed and accuracy with mixed and conditional regression

Human performance in cognitive testing and experimental psychology is expressed in terms of response speed and accuracy. Data analysis is often limited to either speed or accuracy, and/or to crude summary measures like mean response time (RT) or the percentage correct responses. This paper proposes the use of mixed regression for the psychometric modeling of response speed and accuracy in testing and experiments. Mixed logistic regression of response accuracy extends logistic item response theory modeling to multidimensional models with covariates and interactions. Mixed linear regression of response time extends mixed ANOVA to unbalanced designs with covariates and heterogeneity of variance. Related to mixed regression is conditional regression, which requires no normality assumption, but is limited to unidimensional models. Mixed and conditional methods are both applied to an experimental study of mental rotation. Univariate and bivariate analyzes show how within-subject correlation between response and RT can be distinguished from between-subject correlation, and how latent traits can be detected, given careful item design or content analysis. It is concluded that both response and RT must be recorded in cognitive testing, and that mixed regression is a versatile method for analyzing test data.I am grateful to Rogier Donders for putting his data at my disposal.     

A person-fit index for polytomous rasch models,latent class models,and their mixture generalizations

A normally distributed person-fit index is proposed for detecting aberrant response patterns in latent class models and mixture distribution IRT models for dichotomous and polytomous data.This article extends previous work on the null distribution of person-fit indices for the dichotomous Rasch model to a number of models for categorical data. A comparison of two different approaches to handle the skewness of the person-fit index distribution is included.Major parts of this paper were written while the first author worked at the Institute for Science Education, Kiel, Germany. Any opinions expressed in this paper are those of the authors and not necessarily of Educational Testing Service. The results presented in this paper were improved by valuable comments from J. Rost, K. Yamamoto, N.D. Verhelst, E. Bedrick and two anonymous reviewers.     

Karl Schmitz-Moormann: Our Intellectual Legacy From a Great Mind

Karl Schmitz-Moormann's thought as expressed in his last book exemplifies Catholic theology based on realism, flow, evolution, and free will. Categories of creation are reviewed: from nothing, continuous, called forth, informed, and free.     

Distractor effect on the latent inhibition of conditioned flavor aversion in rats

Using a conditioned flavor aversion procedure with rats as subjects, the effect of the addition of a distractor stimulus on the magnitude of the latent inhibition effect was examined. Experiment 1 showed that latent inhibition to vinegar was attenuated by the addition of sucrose during preexposure. On the other hand, sucrose added during conditioning to vinegar did not attenuate latent inhibition. It was also found that the degree of latent inhibition to the vinegar-sucrose compound solution was less when vinegar alone was preexposed (i.e., when sucrose was added only during conditioning) than when the compound solution was preexposed (i.e., when sucrose was added both during preexposure and during conditioning). Experiment 2 gave similar results but with sucrose assigned as the target flavor and vinegar as the distractor. These findings are in full agreement with the generalization decrement account of latent inhibition.     

Subtypes of severe psychological distress among US Air Force remote warriors: A latent class analysis

US Air Force remote warrior personnel include a range of military personnel composed of remotely piloted aircraft aircrew, intelligence operators, and cyber warfare operators. Job duties in these professions entail long work hours, rotating shifts, and regular engagement in combat operations. Although research has identified a number of factors correlated with elevated burnout and emotional distress in this population, little is known about the unique needs of discrete subgroups of distressed personnel. In a sample of 7,550 US Air Force remote warriors, results of latent class analysis yielded four distinct classes. Three of the four reported moderately elevated burnout and job dissatisfaction but differed with respect to demographics and development career stage. The fourth group reported significantly higher levels of emotional distress, burnout, job dissatisfaction, and problems in living. This latter group was comparable to the mid-career group with respect to demographics, although this group had much lower levels of responsibility and indicators of career advancement. Results suggest that, among remote warrior personnel, there are several subtypes of elevated emotional distress. Prevention and intervention strategies that are matched to each subtype may yield better occupational and mental health outcomes than universal, “one size fits all” strategies.     

Chinese college students' general and relationship‐specific representations of adult attachment: Variable‐centred and person‐centred analysis

Formerly, researchers often treated adult attachment as a trait‐like construct with consistency across relationship contexts. However, recent studies have shown that people possess multiple relationship‐specific attachment representations, and inter‐correlations among them are only in a small‐to‐medium range. The aim of this study is to test whether these variable‐centred results could be replicated in China and further supplement them with a person‐centred analysis focusing on identifying prototypical patterns of multiple working models across relationships. We administrated measurements of general and four relationship‐specific (mother/father/best friend/romantic partner) working models and indicators of psychological adjustment upon 302 Chinese college students. Results from variable‐centred analysis demonstrated the cross‐relationship variability in working models. Furthermore, global indicators of psychological adjustment were better predicted by general models, while relationship‐specific indicators were better predicted by corresponding relationship‐specific models. These results largely replicate previous Western studies, supporting the existence of multiple attachment representations in China. In person‐centred analysis, a latent profile analysis identified four typical classes of working model profiles: all‐average, all‐secure, romantic‐insecure and peer‐secure. These classes differed not only in the cross‐relationship variability of their working models, but also in their levels of psychological adjustment. These interesting patterns may have theoretical implications and are worthy of further examination.     

Impact of treatment integrity on intervention effectiveness

Treatment integrity has cogent implications for intervention effectiveness. Understanding these implications is an important, but often neglected, undertaking in behavior analysis. This paper reviews current research on treatment integrity in applied behavior analysis. Specifically, we review research evaluating the relation between integrity failures and the efficacy of behavioral interventions. Avenues for future research are provided.     

Predictors of children's prosocial lie-telling: Motivation, socialization variables, and moral understanding

Children tell prosocial lies for self- and other-oriented reasons. However, it is unclear how motivational and socialization factors affect their lying. Furthermore, it is unclear whether children’s moral understanding and evaluations of prosocial lie scenarios (including perceptions of vignette characters’ feelings) predict their actual prosocial behaviors. These were explored in two studies. In Study 1, 72 children (36 second graders and 36 fourth graders) participated in a disappointing gift paradigm in either a high-cost condition (lost a good gift for a disappointing one) or a low-cost condition (received a disappointing gift). More children lied in the low-cost condition (94%) than in the high-cost condition (72%), with no age difference. In Study 2, 117 children (42 preschoolers, 41 early elementary school age, and 34 late elementary school age) participated in either a high- or low-cost disappointing gift paradigm and responded to prosocial vignette scenarios. Parents reported on their parenting practices and family emotional expressivity. Again, more children lied in the low-cost condition (68%) than in the high-cost condition (40%); however, there was an age effect among children in the high-cost condition. Preschoolers were less likely than older children to lie when there was a high personal cost. In addition, compared with truth-tellers, prosocial liars had parents who were more authoritative but expressed less positive emotion within the family. Finally, there was an interaction between children’s prosocial lie-telling behavior and their evaluations of the protagonist’s and recipient’s feelings. Findings contribute to understanding the trajectory of children’s prosocial lie-telling, their reasons for telling such lies, and their knowledge about interpersonal communication.