Good behavior game - study protocol for a randomized controlled trial of a preventive behavior management program in a Swedish school context

Background: Early conduct problems and school failure are prominent risk factors for several adverse outcomes in later life. With the potential of reaching many children at early stages of their life, school-based interventions constitute a valuable approach to universal prevention. Good behavior game (GBG) is a promising school-based behavior management program, having shown immediate reductions in conduct problems along with several long-term positive effects. Adapting interventions to new contexts may however affect their effectiveness. The current study aims to evaluate the effectiveness of a Swedish adaption of GBG under pragmatic conditions. The intervention is hypothesized to reduce conduct problems in the classroom (primary outcome). Secondary analyses will investigate changes in conduct problems in common school areas, classroom climate, teacher collective efficacy, on-task behavior, as well as investigating behavioral management practices, implementation, and barriers to implementation. Methods: This is a cluster-randomized trial with two parallel groups. Schools will be randomized (1,1, stratified by their areas sociodemographic index score) to be provided training in GBG or perform business-as-usual. The intervention and data collection lasts for a school year. Data will be collected at three time points: at baseline in the beginning of the school year (prior to training in GBG), after three months, and after nine months (at the end of the school year; primary endpoint). Data consists of teacher-rated measures of conduct problems, classroom climate, teacher collective efficacy, behavior management practices, and implementation factors, along with demographic factors. In addition, data will be collected by independent and blinded observers using corresponding measures in a subset of randomly chosen classrooms. Procedural fidelity will be rated and collected by GBG-trainers during nine observations throughout the school year. Statistical analysis will include frequentist intention-to-treat analysis, and comparisons of estimates with a corresponding Bayesian model using weakly informative priors. The study has currently completed data collection. Discussion: This study will provide knowledge in universal prevention and school-based interventions with high reach, as well as specific knowledge concerning the effectiveness of an adapted version of GBG under real-world conditions, along with factors affecting its implementation and effects.