A semiparametric approach for item response function estimation to detect item misfit

When scaling data using item response theory, valid statements based on the measurement model are only permissible if the model fits the data. Most item fit statistics used to assess the fit between observed item responses and the item responses predicted by the measurement model show significant weaknesses, such as the dependence of fit statistics on sample size and number of items. In order to assess the size of misfit and to thus use the fit statistic as an effect size, dependencies on properties of the data set are undesirable. The present study describes a new approach and empirically tests it for consistency. We developed an estimator of the distance between the predicted item response functions (IRFs) and the true IRFs by semiparametric adaptation of IRFs. For the semiparametric adaptation, the approach of extended basis functions due to Ramsay and Silverman (2005) is used. The IRF is defined as the sum of a linear term and a more flexible term constructed via basis function expansions. The group lasso method is applied as a regularization of the flexible term, and determines whether all parameters of the basis functions are fixed at zero or freely estimated. Thus, the method serves as a selection criterion for items that should be adjusted semiparametrically. The distance between the predicted and semiparametrically adjusted IRF of misfitting items can then be determined by describing the fitting items by the parametric form of the IRF and the misfitting items by the semiparametric approach. In a simulation study, we demonstrated that the proposed method delivers satisfactory results in large samples (i.e., N ≥ 1,000).     

Economic Predictors of Differences in Interview Faking Between Countries: Economic Inequality Matters,Not the State of Economy

Many companies recruit employees from different parts of the globe, and faking behavior by potential employees is a ubiquitous phenomenon. It seems that applicants from some countries are more prone to faking compared to others, but the reasons for these differences are largely unexplored. This study relates country-level economic variables to faking behavior in hiring processes. In a cross-national study across 20 countries, participants (N = 3,839) reported their faking behavior in their last job interview. This study used the random response technique (RRT) to ensure participants’ anonymity and to foster honest answers regarding faking behavior. Results indicate that general economic indicators (gross domestic product per capita [GDP] and unemployment rate) show negligible correlations with faking across the countries, whereas economic inequality is positively related to the extent of applicant faking to a substantial extent. These findings imply that people are sensitive to inequality within countries and that inequality relates to faking, because inequality might actuate other psychological processes (e.g., envy) which in turn increase the probability for unethical behavior in many forms.     

Affect,meaning in life,and life satisfaction among immigrants and non-immigrants: A moderated mediation model

Current Psychology - Immigration has become a global phenomenon as part of modern life. However, immigrants often demonstrate negative emotional states following the immigration process, which may...     

Direction of Effects in Multiple Linear Regression Models

Previous studies analyzed asymmetric properties of the Pearson correlation coefficient using higher than second order moments. These asymmetric properties can be used to determine the direction of dependence in a linear regression setting (i.e., establish which of two variables is more likely to be on the outcome side) within the framework of cross-sectional observational data. Extant approaches are restricted to the bivariate regression case. The present contribution extends the direction of dependence methodology to a multiple linear regression setting by analyzing distributional properties of residuals of competing multiple regression models. It is shown that, under certain conditions, the third central moments of estimated regression residuals can be used to decide upon direction of effects. In addition, three different approaches for statistical inference are discussed: a combined D’Agostino normality test, a skewness difference test, and a bootstrap difference test. Type I error and power of the procedures are assessed using Monte Carlo simulations, and an empirical example is provided for illustrative purposes. In the discussion, issues concerning the quality of psychological data, possible extensions of the proposed methods to the fourth central moment of regression residuals, and potential applications are addressed.     

Social judgment of aggressive language: Effects of target and sender sex on the evaluation of slurs

We investigated the influence of the sex of the target and the sex of the sender on the judgment of slurs (verbal derogation). From previous research, we selected and clustered slurs into seven categories and respondents rated their degree of perceived insult in two consecutive questionnaire surveys (N = 281 and N = 224, respectively). Results confirm that slurs are generally judged as being more insulting when directed towards females than towards males. In comparison, differences in sex of sender were small. When directed towards females, slurs referring to “being loose” were rated as the most insulting. For both target sexes, remarks referring to homosexuality and physical unattractiveness were among those rated as the most insulting. Least insulting were slurs referring to unethical acts, lack of intelligence and cowardliness. A sex of respondent effect was found, suggesting that women rated slurs generally more insulting than men. The pattern of results showed considerable stability across surveys attesting for the reliability of the method for measuring the social evaluation of slurs.     

Content‐specific gender differences in emotion ratings from early to late adulthood

The investigation of gender differences in emotion has attracted much attention given the potential ramifications on our understanding of sexual differences in disorders involving emotion dysregulation. Yet, research on content‐specific gender differences across adulthood in emotional responding is lacking. The aims of the present study were twofold. First, we sought to investigate to what extent gender differences in the self‐reported emotional experience are content specific. Second, we sought to determine whether gender differences are stable across the adult lifespan. We assessed valence and arousal ratings of 14 picture series, each of a different content, in 94 men and 118 women aged 20 to 81. Compared to women, men reacted more positively to erotic images, whereas women rated low‐arousing pleasant family scenes and landscapes as particularly positive. Women displayed a disposition to respond with greater defensive activation (i.e., more negative valence and higher arousal), in particular to the most arousing unpleasant contents. Importantly, significant interactions between gender and age were not found for any single content. This study makes a novel contribution by showing that gender differences in the affective experiences in response to different contents persist across the adult lifespan. These findings support the “stability hypothesis” of gender differences across age.     

Leisure activities,caregiving demands and catecholamine levels in dementia caregivers

This study examined whether satisfaction from leisure activities moderates the relationship between caregiving demands (i.e., hours per day spent caring for a spouse with dementia) and resting levels of the catecholamines norepinephrine (NE) and epinephrine (EPI). Spousal caregivers (n?=?107; mean age?=?73.95?±?8.12 years) were assessed in home for plasma levels of NE and EPI, amount of care provided, and leisure satisfaction. Regression was used to determine whether leisure satisfaction moderated the relationship between hours providing care per day and catecholamine levels. A significant interaction was found between hours caregiving and leisure satisfaction for NE, but not for EPI. Post hoc regressions were conducted for both NE and EPI. At low leisure satisfaction, time spent caring for a spouse was positively associated with plasma NE (β?=?0.41; p?=?0.005) and EPI (β?=?0.44; p?=?0.003). In contrast, at high levels of satisfaction, time caregiving was not significantly associated with plasma NE (β?=?–0.08; p?=?0.57) or EPI (β?=?0.23; p?=?0.12). These findings suggest that leisure satisfaction may protect caregivers from increases in catecholamines, which have been implicated in cardiovascular risk. Further support for these findings may impact psychological treatments for distressed caregivers.     

Validation of the SASB Introject Surface in a Norwegian Clinical and Nonclinical Sample

Aronow, Reznikoff, and Moreland (this issue) have written a thoughtful contribution to the debate on the status of nomothetic and idiographic approaches to the Rorschach test. One of the interesting and attractive features of the current Rorschach er a is—as the Rorschach has experienced a resurgence of interest—the continuing interest in the foundations of the test and the historic antecedents to contemporary thought about the Rorschach (cf. Handler, 1994). One cannot consider Rorschach's seminal insights or those of the first and second generation and not deepen one's contemporary understanding and practice. In other words, the more you know about the test, the better "Rorschacher" you will be. This is witness to the test's utility and profundity. For this we may be grateful for the thought-provoking contribution of Aronow and his colleagues.     

Maintained Individual Data Distributed Likelihood Estimation (MIDDLE)

Maintained Individual Data Distributed Likelihood Estimation (MIDDLE) is a novel paradigm for research in the behavioral, social, and health sciences. The MIDDLE approach is based on the seemingly impossible idea that data can be privately maintained by participants and never revealed to researchers, while still enabling statistical models to be fit and scientific hypotheses tested. MIDDLE rests on the assumption that participant data should belong to, be controlled by, and remain in the possession of the participants themselves. Distributed likelihood estimation refers to fitting statistical models by sending an objective function and vector of parameters to each participant’s personal device (e.g., smartphone, tablet, computer), where the likelihood of that individual’s data is calculated locally. Only the likelihood value is returned to the central optimizer. The optimizer aggregates likelihood values from responding participants and chooses new vectors of parameters until the model converges. A MIDDLE study provides significantly greater privacy for participants, automatic management of opt-in and opt-out consent, lower cost for the researcher and funding institute, and faster determination of results. Furthermore, if a participant opts into several studies simultaneously and opts into data sharing, these studies automatically have access to individual-level longitudinal data linked across all studies.     

Elternschaft, Krebs und Kindersorgen

Background

The diagnosis of parental cancer may destabilize the whole family, parents and children as well. The Hamburg children of somatically ill parents (COSIP) intervention supports parental skills and adaptation of children to the situation. There is currently no evidence for criteria to determine which family members should be involved in the COSIP intervention, predominantly the parents (parent setting), the children (child setting) or both (family setting).

Aim of the study

Data from a multicentre study were analyzed with respect to the predominant intervention settings, the correlation between setting and aims of intervention as well as variables that predict the involvement of children in the intervention.

Material and methods

A total of 203 documented cases were analyzed. Different variables that had been documented by the therapists were included in a regression analysis model in order to identify predictive variables.

Results

In 142 cases the intervention was carried out in a specific intervention setting. In 57?% of the cases children were involved (32?% family setting and 25?% child setting). A systematic relationship between the reported intervention aims and the intervention setting was not detected. The most powerful predictor was the existence of emotional problems of children as reported by the child itself.

Conclusions

Decision-making on intervention settings should therefore take the assessment of emotional symptoms of children by the means of age-appropriate self-reporting tools into consideration. Further investigations are needed to reveal variables concerning needs, motivation and capabilities of the family members as well as institutional conditions.