Toward Customer-Centric Organizational Science: A Common Language Effect Size Indicator for Multiple Linear Regressions and Regressions With Higher-Order Terms

• 成果类型: Article
• 署名作者: Krasikova, Dina V.; Le, Huy; Bachura, Eric
• 署名单位: University of Texas System; University of Texas at San Antonio; University of Texas System; University of Texas at San Antonio
• 刊物名称: JOURNAL OF APPLIED PSYCHOLOGY
• ISSN/ISSBN: 0021-9010
• DOI: 10.1037/apl0000296
• 发表日期: 2018
• 页码: 659-675
• 关键词: common language effect size indicator; science-practice gap; multiple regression; moderated regression; regression with nonlinear terms

摘要

To address a long-standing concern regarding a gap between organizational science and practice. scholars called for more intuitive and meaningful ways of communicating research results to users of academic research. In this article, we develop a common language effect size index (CL beta) that can help translate research results to practice. We demonstrate how CL beta, can be computed and used to interpret the effects of continuous and categorical predictors in multiple linear regression models. We also elaborate on how the proposed CL beta index is computed and used to interpret interactions and nonlinear effects in regression models. In addition, we test the robustness of the proposed index to violations of normality and provide means for computing standard errors and constructing confidence intervals around its estimates.