Reducing Shrinkage in Diversity Tradeoff Curves for Personnel Selection: Comparing Local Validity Studies, Meta-Analysis, and Bayes Analysis

• 成果类型: Article; Early Access
• 署名作者: Tang, Chen; Newman, Daniel A.; Song, Q. Chelsea; Wee, Serena
• 署名单位: American University; University of Illinois System; University of Illinois Urbana-Champaign; Indiana University System; IU Kelley School of Business; Indiana University Bloomington; University of Western Australia
• 刊物名称: JOURNAL OF APPLIED PSYCHOLOGY
• ISSN/ISSBN: 0021-9010
• DOI: 10.1037/apl0001376
• 发表日期: 2026
• 关键词: adverse impact; publication bias; cognitive-ability; JOB-PERFORMANCE; EMPLOYMENT; personality; weights; QUALITY; optimization; predictors

摘要

For reducing adverse impact, the diversity-validity tradeoff curve approach (De Corte et al., 2007) provides sets of selection predictor weights that can often substantially enhance diversity (i.e., increase adverse impact ratio and number of minority job offers), with no loss of job performance in comparison to unit weights (Wee et al., 2014). A key limitation of this diversity-enhancing approach is the tendency for tradeoff curves to shrink, leading to lesser job performance and diversity outcomes upon cross-validation (Song et al., 2017). The current article evaluates and compares tradeoff curve shrinkage (both validity shrinkage and diversity shrinkage) using three types of validity evidence/calibration studies: (a) a local validity study, (b) a meta-analysis (Schmidt & Hunter, 1977), and (c) a Bayes analysis with empirical priors, which is a weighted combination of a local study with a meta-analysis (Newman et al., 2007). Using simulation, we show conditions where each approach performs best, offering recommendations on ideal methods for diversity improvement (reducing shrinkage and maximizing cross-validity) in local selection settings. Results guide selection practitioners in novel methods (integrating the advantages of meta-analysis, Bayes analysis, and Pareto-optimal weighting) to best combine predictors to simultaneously achieve job performance and diversity objectives in local selection settings.