Statistical Properties of Regression Discontinuity Analysis and Comparative Interrupted Time-Series Analysis for Estimating Impacts
Primary Investigator(s): Robin Jacob
Funding Agency: U.S. Department of Education/Institute of Education Sciences
Period: 3/1/2009 - 12/31/2010
This proposal seeks to explore in detail the statistical properties of regression discontinuity analysis and comparative interrupted time series analysis. The project assesses the internal validity and generalizability of the estimated impacts produced by these approaches, as well as their statistical power. The purpose of the study is to help researchers better understand the strengths and limitations of these approaches and to provide them with adequate information to implement these methods effectively, particularly where pragmatic considerations make it useful or necessary to employ alternative methods for measuring the impacts of educational interventions.