Assessing accuracy in close relationships research: A truth and bias approach

Do people accurately perceive their romantic partner? What are the implications of perceiving one’s partner accurately or inaccurately? These questions are frequently debated and researched in psychology, and so researchers need to have methods for assessing accuracy that are flexible enough to answer different theoretical questions. Researchers frequently utilize a variety of different approaches to assess two different forms of accuracy: mean-level bias and correlational accuracy. The main goal of this article is to provide recommendations for the best approaches that relationship researchers can use to assess these types of accuracy. We focus on statistical approaches employing advances in multilevel modeling and, in particular, how West and Kenny’s Truth and Bias model can be especially useful for testing questions of bias and accuracy in perceptions in close relationships. We provide step-by-step approaches of how to implement the models we outline.