HBMIRT: A SAS macro for estimating uni- and multidimensional 1- and 2-parameter item response models in small (and large!) samples.

Item response theory (IRT) has evolved as a standard psychometric approach in recent years, in particular for test construction based on dichotomous (i.e., true/false) items. Unfortunately, large samples are typically needed for item refinement in unidimensional models and even more so in the multidimensional case. However, Bayesian IRT approaches with hierarchical priors have recently been shown to be promising for estimating even complex models in small samples. Still, it may be challenging for applied researchers to set up such IRT models in general purpose or specialized statistical computer programs. Therefore, we developed a user-friendly tool - a SAS macro called HBMIRT - that allows to estimate uni- and multidimensional IRT models with dichotomous items. We explain the capabilities and features of the macro and demonstrate the particular advantages of the implemented hierarchical priors in rather small samples over weakly informative priors and traditional maximum likelihood estimation with the help of a simulation study. The macro can also be used with the online version of SAS OnDemand for Academics that is freely accessible for academic researchers.

Beliefs about emotions predict psychological stress related to somatic symptoms.

BACKGROUND: Previous research has shown that the more people believe their emotions are controllable and useful (BECU), the less they generally report psychological distress. Psychological distress, in turn, impacts health outcomes, and is among the most frequently reported complaints in psychotherapeutic and psychosomatic practice. OBJECTIVE: We aimed to examine how BECU predicts psychological distress related to somatic symptoms in a prospective sample from the general population and to replicate this association in two cross-sectional samples of psychosomatic patients. METHODS: We applied a panel design with an interval of 2 weeks between T1 and T2 in general-population panel-participants (N = 310), assessing BECU and psychological distress related to somatic symptoms via validated self-report measures. Moreover, we cross-sectionally replicated the relationship between BECU and psychological distress in a clinical sample of psychosomatic outpatients diagnosed with somatoform disorders (n = 101) or without somatoform disorders (n = 628). RESULTS: BECU predicted over and above the lagged criterion panel-participants' psychological distress related to somatic symptoms, ß = -.18, p < .001. BECU was also cross-sectionally related to psychological distress in our clinical replication-sample of psychosomatic outpatients diagnosed with somatoform disorders, rS (87) = -.33, p = .002 and in those without, rS (557) = -.21, p < .001. CONCLUSIONS: BECU as a malleable way of thinking about emotions predicted psychological distress related to somatic symptoms in general-population panel-participants and correlated with the same in two clinical replication samples. BECU thus becomes a promising treatment target in psychotherapeutic approaches.

Comparing group means with the total mean in random samples, surveys, and large-scale assessments: A tutorial and software illustration.

In many disciplines of the social sciences, comparisons between a group mean and the total mean is a common but also challenging task. As one solution to this statistical testing problem, we propose using linear regression with weighted effect coding. For random samples, this procedure is straightforward and easy to implement by means of standard statistical software. However, for complex or clustered samples with imputed or weighted data, which are common in survey analyses, there is a lack of easy-to-use software solutions. In this paper, we discuss scenarios that are commonly encountered in the social sciences such as heterogeneous variances, weighted samples, and clustered samples, and we describe how group means can be compared to the total mean in these situations. We introduce the R package eatRep, which is a front end that makes the presented methods easily accessible for researchers. Two empirical examples, one using survey data (MIDUS 1) and the other using large-scale assessment data (PISA 2015), are given for illustration. Annotated R code to run group to total mean comparisons is provided.

Does Respect Foster Tolerance? (Re)analyzing and Synthesizing Data From a Large Research Project Using Meta-Analytic Techniques.

Our own prior research has demonstrated that respect for disapproved others predicts and might foster tolerance toward them. This means that without giving up their disapproval of others' way of life, people can tolerate others when they respect them as equals (outgroup respect-tolerance hypothesis). Still, there was considerable variation in the study features. Moreover, the studies are part of a larger research project that affords many additional tests of our hypothesis. To achieve integration along with a more robust understanding of the relation between respect and tolerance, we (re)analyzed all existing data from this project, and we synthesized the results with the help of meta-analytic techniques. The average standardized regression coefficient, which describes the relationship between respect and tolerance, was 0.25 (95% confidence interval [CI] = [0.16, 0.34]). In addition to this overall confirmation of our hypothesis, the size of this coefficient varied with a number of variables. It was larger for numerical majorities than for minorities, smaller for high-status than for low-status groups, and larger for religious than for life-style groups. These findings should inspire further theory development and spur growth in the social-psychological literature on tolerance.

Prior Specification for More Stable Bayesian Estimation of Multilevel Latent Variable Models in Small Samples: A Comparative Investigation of Two Different Approaches.

Bayesian approaches for estimating multilevel latent variable models can be beneficial in small samples. Prior distributions can be used to overcome small sample problems, for example, when priors that increase the accuracy of estimation are chosen. This article discusses two different but not mutually exclusive approaches for specifying priors. Both approaches aim at stabilizing estimators in such a way that the Mean Squared Error (MSE) of the estimator of the between-group slope will be small. In the first approach, the MSE is decreased by specifying a slightly informative prior for the group-level variance of the predictor variable, whereas in the second approach, the decrease is achieved directly by using a slightly informative prior for the slope. Mathematical and graphical inspections suggest that both approaches can be effective for reducing the MSE in small samples, thus rendering them attractive in these situations. The article also discusses how these approaches can be implemented in Mplus.

Disapproved, but Tolerated: The Role of Respect in Outgroup Tolerance.

We conducted two studies to test the hypothesis that respect for disapproved outgroups increases tolerance toward them. In Study 1, we employed a panel sample of supporters of the Tea Party movement in the United States and found that Tea Party supporters' respect for homosexuals and Muslims as equal fellow citizens positively predicted Tea Party supporters' tolerance toward these groups. There was no indication that alternative recognition processes (i.e., achievement recognition or need recognition) played a similar role in the development of tolerance. Study 2 replicated the respect-tolerance link with the experimental method and a more comprehensive measure of tolerance. In particular, it demonstrated that the link also holds with regard to tolerance in the public or political sphere. The wider implications of our research for societal pluralism are discussed.

Politicization as an antecedent of polarization: Evidence from two different political and national contexts.

Using longitudinal research designs, we examine the role of politicization in the development of polarization. We conducted research in two different political and national contexts. In Study 1, we employ a panel sample of supporters of the Tea Party movement in the United States and examine the relationship between the strength of their politicization and their subsequent feelings towards conservatives versus liberals (affective polarization) as well as their subsequent perceptions of commonalities with conservatives versus liberals (cognitive polarization). In Study 2, we employ a panel sample of members of the lesbian, gay, bisexual, transgender, and intersex (LGBTI) community in Germany and examine the politicization-polarization link with regard to feelings towards, and perceived commonalities with, feminists versus supporters of a populist right-wing political party. We obtained converging evidence suggesting that politicization promotes both affective and cognitive polarization. There was also some, but very limited evidence pointing to reverse causation. The danger of escalating polarization is discussed.

A Computationally More Efficient and More Accurate Stepwise Approach for Correcting for Sampling Error and Measurement Error.

Over the last decade or two, multilevel structural equation modeling (ML-SEM) has become a prominent modeling approach in the social sciences because it allows researchers to correct for sampling and measurement errors and thus to estimate the effects of Level 2 (L2) constructs without bias. Because the latent variable modeling software Mplus uses maximum likelihood (ML) by default, many researchers in the social sciences have applied ML to obtain estimates of L2 regression coefficients. However, one drawback of ML is that covariance matrices of the predictor variables at L2 tend to be degenerate, and thus, estimates of L2 regression coefficients tend to be rather inaccurate when sample sizes are small. In this article, I show how an approach for stabilizing covariance matrices at L2 can be used to obtain more accurate estimates of L2 regression coefficients. A simulation study is conducted to compare the proposed approach with ML, and I illustrate its application with an example from organizational research.

A Bayesian Approach to More Stable Estimates of Group-Level Effects in Contextual Studies.

Multilevel analyses are often used to estimate the effects of group-level constructs. However, when using aggregated individual data (e.g., student ratings) to assess a group-level construct (e.g., classroom climate), the observed group mean might not provide a reliable measure of the unobserved latent group mean. In the present article, we propose a Bayesian approach that can be used to estimate a multilevel latent covariate model, which corrects for the unreliable assessment of the latent group mean when estimating the group-level effect. A simulation study was conducted to evaluate the choice of different priors for the group-level variance of the predictor variable and to compare the Bayesian approach with the maximum likelihood approach implemented in the software Mplus. Results showed that, under problematic conditions (i.e., small number of groups, predictor variable with a small ICC), the Bayesian approach produced more accurate estimates of the group-level effect than the maximum likelihood approach did.

Examining the presence and determinants of operational momentum in childhood.

The operational momentum (OM) effect describes a systematic bias in estimating the outcomes of simple addition and subtraction problems. Outcomes of addition problems are overestimated while outcomes of subtraction problems are underestimated. The origin of OM remains debated. First, a flawed uncompression of numerical information during the course of mental arithmetic is supposed to cause OM due to linear arithmetic operations on a compressed magnitude code. Second, attentional shifts along the mental number line are thought to cause OM. A third hypothesis explains OM in 9-month olds by a cognitive heuristic of accepting more (less) than the original operand in addition (subtraction) problems. The current study attempts to disentangle these alternatives and systematically examines potential determinants of OM, such as reading fluency which has been found to modulate numerical-spatial associations. A group of 32 6- and 7-year-old children was tested in non-symbolic addition and subtraction problems, in which they had to choose the correct outcome from an array of several possible outcomes. Reading capacity was assessed for half of the children while attentional measures were assessed in the other half. Thirty-two adults were tested with the identical paradigm to validate its potential of revealing OM. Children (and adults) were readily able to solve the problems. We replicated previous findings of OM in the adults group. Using a Bayesian framework we observed an inverse OM effect in children, i.e., larger overestimations for subtraction compared to addition. A significant correlation between children's level of attentional control and their propensity to exhibit OM was observed. The observed pattern of results, in particular the inverse OM in children is hard to reconcile with the previously proposed theoretical frameworks. The observed link between OM and the attentional system might be interpreted as evidence partially supporting the attentional shift hypothesis.