Identifying Common Methods Variance With Data Collected From A Single Source: An Unresolved Sticky Issue

Abstract

Common methods variance that can result when two or more constructs are measured by a single rater or source was examined using Within and Between Analysis (WABA). Levels of analysis effects were assessed for single-source leadership and outcome ratings obtained using surveys completed by the followers of managers employed by a multidivisional Fortune 500 high technology organization. The alignment of singleand multiple-source effects with the analytic procedures, a critique of recommended procedures for addressing problems with single-source variance, an alternative conceptual framework, and strategies to address problems with research involving questionnaire! survey self-report measures are discussed.