Justin A. DeSimone

Exploring Joint Variance Between Independent Variables and a Criterion Meaning, Effect, and Size

Current methods used in the analysis and interpretation of behavioral data tend to ignore a potentially important explanatory component. That component is the joint variance shared between predictors in explaining variance in the outcome variable. The authors provide an example of joint variance and how it could be interpreted. The authors believe ignoring this component has inhibited development of explanatory theories. The authors discuss a method developed by Mood for calculating joint explanatory variance. This method was initially developed to better interpret the unique effects of predictors on a criterion but can also be used to gain a better understanding of joint effects as well. They reanalyze published data to demonstrate the contribution of this approach in analyzing and interpreting behavioral data. They also provide a method for calculating the significance of joint variance components.

An item analysis of the conditional reasoning test of aggression

This manuscript uses item response theory (IRT) to estimate item characteristics of the Conditional Reasoning Test of Aggression (CRT-A). Using a sample size of 5,511 respondents, the present analysis provides an accurate assessment of the capability of the CRT-A to measure latent aggression. The one-parameter logistic (1PL) model, two-parameter logistic (2PL) model, and three-parameter logistic (3PL) model are compared before the item analysis. Results suggest that the 2PL model is the most appropriate dichotomous IRT model for describing the item characteristics of the CRT-A. Potential multdimensionality in the CRT-A is also examined. Results suggest that CRT-A items work as theoretically intended, with the probability of selecting an aggressive response increasing with latent trait levels. Information curves indicate that the CRT-A is best suited for use with individuals who are high on latent aggression. Exploratory analyses include an examination of polytomous IRT models and DIF comparing student and employee respondents. The results have implications for future research using the CRT-A as well as the identification of populations appropriate for measurement using this assessment tool.

Development and Validation of the Five-by-Five Resilience Scale:

This article introduces a new measure of resilience and five related protective factors. The Five-by-Five Resilience Scale (5×5RS) is developed on the basis of theoretical and empirical considerations. Two samples (N = 475 and N = 613) are used to assess the factor structure, reliability, convergent validity, and criterion-related validity of the 5×5RS. Confirmatory factor analysis supports a bifactor model. The 5×5RS demonstrates adequate internal consistency as evidenced by Cronbach’s alpha and empirical reliability estimates. The 5×5RS correlates positively with the Connor–Davidson Resilience Scale (CD-RISC), a commonly used measure of resilience. The 5×5RS exhibits similar criterion-related validity to the CD-RISC as evidenced by positive correlations with satisfaction with life, meaning in life, and secure attachment style as well as negative correlations with rumination and anxious or avoidant attachment styles. 5×5RS scores are positively correlated with healthy behaviors such as exercise and negatively correlated with sleep difficulty and symptomology of anxiety and depression. The 5×5RS incrementally explains variance in some criteria above and beyond the CD-RISC. Item responses are modeled using the graded response model. Information estimates demonstrate the ability of the 5×5RS to assess individuals within at least one standard deviation of the mean on relevant latent traits.

New Techniques for Evaluating Temporal Consistency

Temporal consistency (otherwise known as test-retest reliability) is often calculated by correlating test scores for participants who have taken a test on two separate occasions. Unfortunately, analysis of the relationship between total scores across test administrations potentially ignores information related to the consistency of individual items, item interrelationships, and individual respondents. The purpose of this article is to introduce a set of new statistics intended to address these issues. Illustrative examples are provided to demonstrate the potential utility of each proposed statistic and provide proof of concept. Each of the proposed statistics works as intended, providing evidence that this set of analyses can be used to enhance the assessment of temporal consistency.

The Differential Impacts of Two Forms of Insufficient Effort Responding: IMPACT OF DIFFERENT TYPES OF IER

Recent years have seen a renewed interest in insufficient effort responding (IER). Previous research has demonstrated that IER can have detrimental effects on survey research ranging from introducing untrustworthy data to influencing psychometric and statistical results. The present simulations examine two forms of IER, straightlining (SL) and random responding (RR), in an attempt to determine whether the presence of these response patterns have differential impacts on data. In three studies, we explore the combined effects of extreme SL and RR, the effects of full and partial RR, and the effects of full and partial SL on scale characteristics such as inter-item correlations, alpha, and component structure. We also explore how various IER response distributions may influence these statistics. Empirical results demonstrate a tendency for SL to increase and RR to decrease the magnitude of inter-item correlations, alpha, and the first component eigenvalue. Results also indicate that the impact of SL may be more pronounced than the impact of RR in the organisational sciences. It is important for researchers to consider the type of IER in addition to the prevalence of IER in a sample prior to conducting statistical analyses.

The Abbreviated Character Strengths Test (ACST): A Preliminary Assessment of Test Validity

ABSTRACT The 24-item Abbreviated Character Strengths Test (ACST) was developed to efficiently measure character strengths (Peterson, Park, & Castro, 2011). However, its validity for this purpose has not yet been sufficiently established. Using confirmatory factor analysis to test a series of structural models, only a modified bifactor model showed reasonably acceptable fit. Further analyses of this model failed to demonstrate measurement invariance between male and female respondents. Relationships between ACST dimension and Big Five personality trait scores were generally weak-to-moderate, and support for hypotheses regarding each ACST virtues expected correspondence with specific Big Five dimensions was mixed. Finally, scores on ACST dimensions accounted for a combined 12% of the variance in satisfaction with life scores, after controlling for socially desirability. Although an abbreviated measure of character strengths represents a practical need, considerable improvements to the ACST are needed for it to adequately meet this purpose.

If It Were Only That Easy: The Use of Meta-Analytic Research by Organizational Scholars

This paper evaluates how researchers are currently citing meta-analytic results and provides specific recommendations for interpreting the information provided by meta-analysis (MA). The past four decades have seen a proliferation of MA research across the organizational sciences and myriad improvements to how MA is conducted. MAs are cited more frequently than individual primary studies and have a substantial influence on subsequent research and theorizing. Yet the consumption of meta-analytic results in organizational scholarship remains superficial. We evaluate citation practices for four seminal MAs and find that authors predominantly interpret meta-analytic findings in the simplest way possible: as evidence of the existence of a relationship between variables. In focusing only on this basic finding, citing authors neglect the complexity and rich detail provided by MA. We offer advice for how researchers can more effectively leverage the strengths of meta-analytic findings to inform subsequent research by taking advantage of the benefits that meta-analytic methodology can provide for the explanation of organizational phenomena.

Insufficient Effort Responding as a Partial Function of Implicit Aggression

In recent years, researchers have devoted greater attention to insufficient effort responding (IER), in which participants fail to attend to instructions, do not read item content carefully, or intentionally engage in random responding. While IER is typically considered a purely methodological concern, recent research has begun to examine whether it also has a substantive basis (e.g., personality). Here we extend the nomological network surrounding IER by examining the role of implicit aggression. In three studies, we demonstrate that higher levels of implicit aggression are indeed related to IER even after controlling for previously established correlates of IER. Furthermore, we also demonstrate that IER, as measured by the selection of illogical responses to Conditional Reasoning Tests of Aggression, can predict theoretically relevant behavioral criteria. The theoretical and practical implications of this work are discussed.

Exemplary Exercises for Entrepreneurship Education

As interest in entrepreneurship continues to rise, educators should attempt to engage students through the use of interactive exercises that demonstrate key concepts and provide opportunities to practice what they learn. This article aims to describe four ideas for projects and assignments relevant to entrepreneurship education. Each of these tasks can be used to introduce concepts, initiate discussion, and provide students with the opportunity to gain experience with certain entrepreneurial activities. These exercises may also be useful when teaching courses on related topics in management. Instructors should think critically about how to tie course concepts to each of the exercises, tailoring each to fit the needs of their specific class.

Development and Validation of the Five-by-Five Resilience Scale

Resilience is a key component of positive organizational scholarship and positive psychology. Resilience is a protective factor which allows individuals to adapt to and manage stress or adverse cir...