Solving the Puzzle of Null Violent Media Effects

Public Policy Relevance Statement There are good theoretical and practical reasons to expect that exposure to violent media (e.g., TV programs, movies, video games) will increase aggression. This article proposes several solutions to the puzzle of why some studies find nonsignificant violent media effects, even though most studies find significant effects. Over the past half-century, many professional and scientific organizations have issued statements about the harmful effects of violent media on children and adolescents. Most pediatricians, media researchers, and parents also believe that violent media can be harmful. Although most studies report significant violent media effects, some report null effects. In this article, we address the puzzle of why some studies obtain null effects. Some possible factors include the use of inappropriate or excessive number of covariates, small samples, trait measures when state measures are more appropriate, poor predictor and outcome measures, and poor procedures to control for suspicion. We also discuss statistical, methodological, and theoretical issues that underlie some "failures" to replicate in experimental, cross-sectional, and longitudinal studies. The differences between studies that do and do not report significant violent media effects are explainable; sometimes they are intentional because different scholars have different objectives. We offer best practice suggestions for conducting violent media research, which we hope will be useful for editors, reviewers, researchers, pediatricians, politicians, parents, and others trying to evaluate violent media research. Finally, we also show the importance of our analyses and suggestions for other media research, for other research topics, and for the replication crisis in psychology.