Daniel A. Newman

How important are job attitudes? Meta-analytic comparisons of integrative behavioral outcomes and time sequences

Drawing on the compatibility principle in attitude theory, we propose that overall job attitude (job satisfaction and organizational commitment) provides increasingly powerful prediction of more integrative behavioral criteria (focal performance, contextual performance, lateness, absence, and turnover combined). The principle was sustained by a combination of meta-analysis and structural equations showing better fit of unified versus diversified models of meta-analytic correlations between those criteria. Overall job attitude strongly predicted a higher-order behavioral construct, defined as desirable contributions made to one’s work role (r .59). Time-lagged data also supported this unified, attitude-engagement model.

Longitudinal modeling with randomly and systematically missing data: A simulation of ad hoc, maximum likelihood, and multiple imputation techniques.

For organizational research on individual change, missing data can greatly reduce longitudinal sample size and potentially bias parameter estimates. Within the structural equation modeling framework, this article compares six missing data techniques (MDTs): listwise deletion, pairwise deletion, stochastic regression imputation, the expectation-maximization (EM) algorithm, full information maximization likelihood (FIML), and multiple imputation (MI). The rationale for each technique is reviewed, followed by Monte Carlo analysis based on a threewave simulation of organizational commitment and turnover intentions. Parameter estimates and standard errors for each MDT are contrasted with complete-data estimates, under three mechanisms of missingness (completely random, random, and nonrandom) and three levels of missingness (25%, 50%, and 75%; all monotone missing). Results support maximum likelihood and MI approaches, which particularly outperform listwise deletion for parameters involving many recouped cases. Better standard error estimates are derived from FIML and MI techniques. All MDTs perform worse when data are missing nonrandomly.

Distinguishing differential susceptibility from diathesis–stress: Recommendations for evaluating interaction effects

This report describes the state of the art in distinguishing data generated by differential susceptibility from diathesis-stress models. We discuss several limitations of existing practices for probing interaction effects and offer solutions that are designed to better differentiate differential susceptibility from diathesis-stress models and quantify their corresponding implications. In addition, we demonstrate the utility of these methods by revisiting published evidence suggesting that temperamental difficulty serves as a marker of enhanced susceptibility to early maternal caregiving across a range of outcome domains in the NICHD Study of Early Child Care and Youth Development. We find that, with the exception of mother reports of psychopathology, there is consistent evidence in the Study of Early Child Care and Youth Development that the predictive significance of early sensitivity is moderated by difficult temperament over time. However, differential susceptibility effects emerged primarily for teacher reports of academic skills, social competence, and symptomatology. In contrast, effects more consistent with the diathesis-stress model were obtained for mother reports of social skills and objective tests of academic skills. We conclude by discussing the value of the application of this work to the next wave of Gene × Environment studies focused on early caregiving experiences.

Missing Data Five Practical Guidelines

Missing data (a) reside at three missing data levels of analysis (item-, construct-, and person-level), (b) arise from three missing data mechanisms (missing completely at random, missing at random, and missing not at random) that range from completely random to systematic missingness, (c) can engender two missing data problems (biased parameter estimates and inaccurate hypothesis tests/inaccurate standard errors/low power), and (d) mandate a choice from among several missing data treatments (listwise deletion, pairwise deletion, single imputation, maximum likelihood, and multiple imputation). Whereas all missing data treatments are imperfect and are rooted in particular statistical assumptions, some missing data treatments are worse than others, on average (i.e., they lead to more bias in parameter estimates and less accurate hypothesis tests). Social scientists still routinely choose the more biased and error-prone techniques (listwise and pairwise deletion), likely due to poor familiarity with and misconceptions about the less biased/less error-prone techniques (maximum likelihood and multiple imputation). The current user-friendly review provides five easy-to-understand practical guidelines, with the goal of reducing missing data bias and error in the reporting of research results. Syntax is provided for correlation, multiple regression, and structural equation modeling with missing data.

Gender differences in narcissism: a meta-analytic review.

Despite the widely held belief that men are more narcissistic than women, there has been no systematic review to establish the magnitude, variability across measures and settings, and stability over time of this gender difference. Drawing on the biosocial approach to social role theory, a meta-analysis performed for Study 1 found that men tended to be more narcissistic than women (d = .26; k = 355 studies; N = 470,846). This gender difference remained stable in U.S. college student cohorts over time (from 1990 to 2013) and across different age groups. Study 1 also investigated gender differences in three facets of the Narcissistic Personality Inventory (NPI) to reveal that the narcissism gender difference is driven by the Exploitative/Entitlement facet (d = .29; k = 44 studies; N = 44,108) and Leadership/Authority facet (d = .20; k = 40 studies; N = 44,739); whereas the gender difference in Grandiose/Exhibitionism (d = .04; k = 39 studies; N = 42,460) was much smaller. We further investigated a less-studied form of narcissism called vulnerable narcissism-which is marked by low self-esteem, neuroticism, and introversion-to find that (in contrast to the more commonly studied form of narcissism found in the DSM and the NPI) men and women did not differ on vulnerable narcissism (d = -.04; k = 42 studies; N = 46,735). Study 2 used item response theory to rule out the possibility that measurement bias accounts for observed gender differences in the three facets of the NPI (N = 19,001). Results revealed that observed gender differences were not explained by measurement bias and thus can be interpreted as true sex differences. Discussion focuses on the implications for the biosocial construction model of gender differences, for the etiology of narcissism, for clinical applications, and for the role of narcissism in helping to explain gender differences in leadership and aggressive behavior. Readers are warned against overapplying small effect sizes to perpetuate gender stereotypes.

Emotional intelligence is a second-stratum factor of intelligence: evidence from hierarchical and bifactor models.

This article examines the status of emotional intelligence (EI) within the structure of human cognitive abilities. To evaluate whether EI is a 2nd-stratum factor of intelligence, data were fit to a series of structural models involving 3 indicators each for fluid intelligence, crystallized intelligence, quantitative reasoning, visual processing, and broad retrieval ability, as well as 2 indicators each for emotion perception, emotion understanding, and emotion management. Unidimensional, multidimensional, hierarchical, and bifactor solutions were estimated in a sample of 688 college and community college students. Results suggest adequate fit for 2 models: (a) an oblique 8-factor model (with 5 traditional cognitive ability factors and 3 EI factors) and (b) a hierarchical solution (with cognitive g at the highest level and EI representing a 2nd-stratum factor that loads onto g at λ = .80). The acceptable relative fit of the hierarchical model confirms the notion that EI is a group factor of cognitive ability, marking the expression of intelligence in the emotion domain. The discussion proposes a possible expansion of Cattell-Horn-Carroll theory to include EI as a 2nd-stratum factor of similar standing to factors such as fluid intelligence and visual processing.

Recruitment efforts to reduce adverse impact: targeted recruiting for personality, cognitive ability, and diversity.

Noting the presumed tradeoff between diversity and performance goals in contemporary selection practice, the authors elaborate on recruiting-based methods for avoiding adverse impact while maintaining aggregate individual productivity. To extend earlier work on the primacy of applicant pool characteristics for resolving adverse impact, they illustrate the advantages of simultaneous cognitive ability- and personality-based recruiting. Results of an algebraic recruiting model support general recruiting for cognitive ability, combined with recruiting for conscientiousness within the underrepresented group. For realistic recruiting effect sizes, this type of recruiting strategy greatly increases average performance of hires and percentage of hires from the underrepresented group. Further results from a policy-capturing study provide initial guidance on how features of organizational image can attract applicants with particular job-related personalities and abilities, in addition to attracting applicants on the basis of demographic background.

The stability of personality traits in individuals with borderline personality disorder.

Although stability and pervasive inflexibility are general criteria for Diagnostic and Statistical Manual of Mental Disorders, 4th edition (American Psychiatric Association, 1994) personality disorders (PDs), borderline PD (BPD) is characterized by instability in several domains, including interpersonal behavior, affect, and identity. The authors hypothesized that such inconsistencies notable in BPD may relate to instability at the level of the basic personality traits that are associated with this disorder. Five types of personality trait stability across 4 assessments over 6 years were compared for BPD patients (N = 130 at first interval) and patients with other PDs (N = 302). Structural stability did not differ across groups. Differential stability tended to be lower for 5-factor model (FFM) traits in the BPD group, with the strongest and most consistent effects observed for Neuroticism and Conscientiousness. Growth curve models suggested that these 2 traits also showed greater mean-level change, with Neuroticism declining faster and Conscientiousness increasing faster, in the BPD group. The BPD group was further characterized by greater individual-level instability for Neuroticism and Conscientiousness in these models. Finally, the BPD group was less stable in terms of the ipsative configuration of FFM facet-level profiles than was the other PD group over time. Results point to the importance of personality trait instability in characterizing BPD.

Discriminant Validity of Self-Reported Emotional Intelligence: A Multitrait–Multisource Study

A major stumbling block for emotional intelligence (EI) research has been the lack of adequate evidence for discriminant validity. In a sample of 280 dyads, self- and peer-reports of EI and Big Five personality traits were used to confirm an a priori four-factor model for the Wong and Law Emotional Intelligence Scale (WLEIS) and a five-factor model for Goldberg’s International Personality Item Pool (IPIP). After demonstrating measurement equivalence between self-report and peer-report for both scales, the authors show discriminant validity between the four EI subfacets and Big Five personality traits. This is accomplished through a series of structural equation models fit to the mutitrait-multimethod matrix. Despite their conclusion of discriminant validity, the authors note strong latent correlations between Others’ Emotion Appraisal and trait Agreeableness (φ = .87), between Use of Emotion and trait Conscientiousness (φ = .73), between Regulation of Emotion and trait Neuroticism (φ = −.66), and between Self Emotion Appraisal and trait Neuroticism (φ = −.66). There is also post hoc evidence of potential leniency in self-reported emotion regulation. Results point to the utility of peer-report methods as well as the relative construct validity of various subfacets of self-reported emotional competence.

Using Mixed-Measurement Item Response Theory With Covariates (MM-IRT-C) to Ascertain Observed and Unobserved Measurement Equivalence

Traditional item response theory (IRT) measurement invariance approaches examine measurement equivalence (ME) between observed groups (e.g., race, gender, culture). By contrast, mixed-measurement item response theory (MM-IRT) ascertains ME among unobserved groups (i.e., latent classes [LC] of respondents distinguished by differences in scale use). Both approaches can be integrated by using the Mixed-Measurement Item Response Theory with Covariates (MM-IRT-C) model, in which covariates (i.e., observed characteristics) are modeled in conjunction with LCs, thereby elucidating if ME is attributable to observed and/or unobserved groupings. We first show how this technique can be used to ascertain ME over multiple observed characteristics (categorical and/or continuous) concomitantly, thereby advancing a more general approach to observed ME. Next, we illustrate how the full MM-IRT-C can be used to: (a) infer underlying latent measurement classes (LCs), (b) determine associations of LC membership with observed characteristics, and (c) determine if observed measurement nonequivalence occurs predominantly within a particular latent measurement class. This method is demonstrated using a measure of union citizenship behavior, with years of work experience and gender as covariates. The proposed framework extends organizational ME research from considering a single question (i.e., Is there ME between categorical observed groups?) to addressing eight, separate questions about observed and unobserved ME. The substantive and methodological contributions of this model for rethinking ME and its use in organizational research are discussed.