NotesFAQContact Us
Search Tips
Peer reviewed Peer reviewed
PDF on ERIC Download full text
ERIC Number: ED562743
Record Type: Non-Journal
Publication Date: 2014
Pages: 11
Abstractor: ERIC
Reference Count: 6
Evaluating Non-Randomized Educational Interventions: A Graphical Discussion
Theobald, Roddy; Richardson, Thomas
Society for Research on Educational Effectiveness
A central goal of the education literature is to demonstrate that specific educational interventions--instructional interventions at the student or classroom level, structural interventions at the school level, or funding interventions at the school district level, for example--have a "treatment effect" on student achievement. This paper has three objectives. First, Theobald and Richardson explain both how Single World Intervention Templates (SWITs) unify two existing approaches to causality--potential outcomes and directed acyclic graphs (DAGs)--and their utility as a framework for discussing confounding and causality. Second, Theobald and Richardson introduce a specific SWIT that can be used to discuss confounding and causality in a "pre/post" study of an educational intervention. Finally, Theobald and Richardson use this SWIT to discuss the assumptions necessary for common estimation methods to produce an unbiased estimate of the treatment effect of a non-randomized educational intervention. The study concludes a central goal of this paper is to illustrate the utility of graphs, and single world intervention templates (SWITs) in particular, as a means of communicating these assumptions. Tables and figures are appended.
Society for Research on Educational Effectiveness. 2040 Sheridan Road, Evanston, IL 60208. Tel: 202-495-0920; Fax: 202-640-4401; e-mail:; Web site:
Publication Type: Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: Society for Research on Educational Effectiveness (SREE)