AI Summary
[DOCUMENT_TYPE: instructional_content]
**What This Document Is**
These are lecture notes from EVAL 6970, a graduate-level course on Research on Evaluation at Western Michigan University. The notes focus specifically on experimental and quasi-experimental research designs – core methodologies used to determine the effectiveness of programs and interventions. This 31-page resource delves into the intricacies of establishing causal relationships in evaluation research, moving beyond simple observation to rigorous testing. It’s a detailed record of classroom instruction on advanced evaluation techniques.
**Why This Document Matters**
This resource is invaluable for graduate students in evaluation, research methods, public policy, and related fields. It’s particularly helpful for those preparing to design, implement, or analyze evaluation studies. Professionals already working as evaluators will also find it useful as a refresher on key concepts and a resource for understanding the nuances of different design options. If you’re facing a research project where demonstrating impact is crucial, understanding these designs is essential. It’s best used *alongside* a core textbook and practical application exercises.
**Common Limitations or Challenges**
These notes represent a specific instructor’s approach to the material and should not be considered a substitute for a comprehensive textbook or independent research. The notes are detailed, but they do not offer step-by-step instructions for conducting statistical analyses or implementing specific designs. They also focus on theoretical underpinnings and may not cover all practical considerations encountered in real-world evaluation settings. Access to the full notes does not guarantee success in applying these concepts without further study and practice.
**What This Document Provides**
* An overview of quasi-experimental designs utilizing both control groups and pretests.
* Detailed exploration of interrupted time-series designs.
* Discussion of potential design and power-related issues in evaluation research.
* Examination of various patterns of outcomes observed when comparing treatment and control groups.
* Methods for modeling and addressing selection bias in research designs.
* Visual representations of effect-decay functions to illustrate treatment impacts over time.
* Analysis of designs employing dependent pretest and posttest samples, including variations with double pretests, switching replications, and reversed treatment control groups.