This report by the National Research Council's Committee on Improving Evaluation of Anti-Crime Programs is intended as a guide for agencies and organizations responsible for program evaluation, as well as for researchers who design evaluations and for policy officials committed to basing their decisions on evaluation findings.
The report's first section, "What Questions Should the Evaluation Address?" emphasizes that evaluations should not only determine a program's impact but also the need for the program, its design, its implementation, and its cost-effectiveness. The second section, "When Is It Appropriate to Conduct an Impact Evaluation?" advises that this should be determined in the course of planning to launch the program and will depend on various factors that bear upon the evaluation. The third section of the report discusses how an impact evaluation should be designed. This involves practical and technical considerations related to sampling and the generalizability of results, statistical power, measurement, methods for estimating program effects, and information that helps explain effects. This is followed by an outline of how the evaluation should be implemented. The organizational infrastructure and procedures that support high-quality evaluation are then described. Recommendations accompany each section. 65 references
Downloads
Similar Publications
- A Multivariate Heavy-tailed Integer-valued GARCH Process with EM Algorithm-based Inference
- Acoustic Differential Extraction for Forensic Analysis of Sexual Assault Evidence
- Quadruplex Real-Time qPCR Assay for the Simultaneous Assessment of Total Human DNA, Human Male DNA, DNA Degradation and the Presence of PCR Inhibitors in Forensic Samples: A Diagnostic Tool for STR Typing