PUBLISHED WORK
How rare is rare? How common is common? Empirical issues associated with binary dependent variables with rare or common event rates
Hyun-Soo Woo, John Berns, & Pol Solanelles
Organizational Research Methods
The use of logit and probit models when examining binary dependent variables including those in the form 0/1 (i.e., dummy variables), yes/no, and true/false (hereafter labeled DVs) is commonplace. Yet, the appropriateness and effectiveness of such models are challenged when the event rate of a binary DV is rare or common. To better understand the impact on the field of strategy, we undertook a literature review and assessed recently published research in the Strategic Management Journal. We then utilized Monte Carlo simulations with results showing that as event rates become rarer or more common, issues including biased coefficients, standard error inflation, low statistical power to detect significant effects, and model convergence failure increasingly arise. In addition, small sample sizes amplified these empirical issues. Using a strategy example study, we also show how various analytic tools can lead to different findings when empirical models face an extreme event rate with small sample sizes. Based on our findings, we provide step-by-step guidance for strategy researchers going forward.
Drinking (wine) again: Always the same in a pandemic?
Pol Solanelles, Barry J. Babin, & David A. Locander
Journal of Wine Research
The present research explores the role of wine’s social and coping benefits during stressful times (e.g. COVID-19 shutdown). This research operationalizes one factor that captures perceived value from wine due to social benefits and a second factor that captures the perceived value from wine due to benefits that help one cope with anxious times. A research framework is proposed and explored using mediation analyses. Results across two studies suggest that life situations relate to both wine’s social value and need for coping. Both wine's social value and coping value help drive wine consumption.
Network structures of influence within organizations and implications for HRM
The field of Human Resource Management (HRM) has long recognized the importance of interpersonal influence for employee and organizational effectiveness. HRM research and practice have focused primarily on individuals’ characteristics and behaviors as a means to understand “who” is influential in organizations, with substantially less attention paid to social networks. To reinvigorate a focus on network structures to explain interpersonal influence, the authors present a comprehensive account of how network structures enable and constrain influence within organizations. The authors begin by describing how power and status, two key determinants of individual influence in organizations, operate through different mechanisms, and delineate a range of network positions that yield power, reflect status, and/or capture realized influence. Then, the authors extend initial structural views of influence beyond the positions of individuals to consider how network structures within and between groups – capturing group social capital and/or shared leadership – enable and constrain groups’ ability to influence group members, other groups, and the broader organizational system. The authors also discuss how HRM may leverage these insights to facilitate interpersonal influence in ways that support individual, group, and organizational effectiveness.
Bias in student evaluations: Self-efficacy and identity-threat at play
Amy McMillan, Pol Solanelles, & Bryan Rogers
Studies in Educational Evaluation
The use of peer evaluations to evaluate performance is commonplace, especially in higher education. Yet, researchers and educators have long expressed concerns about the accuracy of such ratings. While research has found student peer evaluations to be consistent with instructor evaluations, rater bias is inherent in all evaluations, and students are not exempt from this. This study examines task completion and identity threat to determine if experience and identity play a role in shaping student peer evaluations. A sample of MBA students evaluated their peers before and after completing a course presentation. Results showed that students’ peer evaluations were significantly “lower” or more critical after having completed the presentation themselves. This study illuminates the importance of experience and training in the implementation of performance evaluations.