Randomized Controlled Trials

This paper covers the topic of randomized controlled trials in social, educational, criminological, health, and other human service sectors. It is studded with illustrations from developed and developing countries. We address the basic ideas that underlie trials in different ways, and cover contemporary definitions and vernacular, some history, and idea of cumulating evidence from such trials including recent work on replication and meta-analyses. Standards for evidence and reporting are considered. We attend to statistical matters and also recognize important non-statistical matters that must be taken into account in designing and executing such trials. Cluster randomized, place randomized, and other designs for such trials are covered on account of their increasing importance. Disciplines Education | Educational Assessment, Evaluation, and Research | Other Education This working paper is available at ScholarlyCommons: http://repository.upenn.edu/gse_pubs/396 1 Title: Randomized Controlled Trials Authors and Affiliations: Robert Boruch (university of Pennsylvania), Rui Yang (American Institutes for Research) , Jordan Hyatt (Drexel University) , Herb Turner III (Analytica, Inc.) Date: October 2016 Prepared for: University Commons, and for Bent Greve (Ed) Handbook of Social Policy Evaluation. Cheltenham UK: Edward Elgar Publishing 0. Introduction This paper covers the topic of randomized controlled trials in social, educational, criminological, health, and other human service sectors. It is studded with illustrations from developed and developing countries. We address the basic ideas that underlie trials in different ways, and cover contemporary definitions and vernacular, some history, and idea of cumulating evidence from such trials including recent work on replication and meta-analyses. Standards for evidence and reporting are considered. We attend to statistical matters and also recognize important non-statistical matters that must be taken into account in designing and executing such trials. Cluster randomized, place randomized, and other designs for such trials are covered on account of their increasing importance. 1.Definitions, Vernacular, and Rationale A randomized controlled trial is a study in which people, entities, or places are randomly allocated to one or more interventions. One of the interventions may be a control condition that receives no special treatment, and which is then construed as the counterfactual. The aim of a randomized controlled trial is to identify causal relationships through (a) a fair comparison of the different interventions in estimating their effects and (b) a legitimate statistical statement of