Moderators and mediators in social work research: Toward a more ecologically valid evidence base for practice

Evidence-based practice involves the consistent and critical consumption of the social work research literature. As methodologies advance, primers to guide such efforts are often needed. In the present work, common statistical methods for testing moderation and mediation are identified, summarized, and corresponding examples, drawn from the substance abuse, domestic violence, and mental health literature, are provided. Findings: Analyses of these third variable effects can provide an optimal fit for the complexity involved in the provision of evidence-based social work services. While a moderator may identify the trait or state requirement for a causal relationship to occur, a mediator is concerned with the transmission of that relationship. In social work practice, these are questions of 'under what conditions and for whom?' and of the 'how?' of behavior change. Implications: Implications include a need for greater attention to these methods among practitioners and evaluation researchers. With knowledge gained through the present review, social workers can benefit from a more ecologically valid evidence base for practice.