Designed to provide researchers clear and informative insight into techniques of meta-analysis, the Third Edition of Methods of Meta-Analysis: Correcting Error and Bias in Research Findings is the most comprehensive text on meta-analysis available today. It is the only book that presents a full and usable treatment of the role of study artifacts in distorting study results, as well as methods for correcting results for such biases and errors.
Chapter 6: Treatment Effects: Experimental Artifacts and their Impact
Treatment Effects: Experimental Artifacts and their Impact
This chapter presents a substantive discussion of the evaluation of experiments and interventions. The next chapter (Chapter 7) presents the quantitative methods and formulas for meta-analysis and other more technical material. For purposes of simplicity, we consider only a two-group experiment. The principles developed here apply equally to more complicated designs. The more complicated designs are discussed in Chapter 8.
This presentation parallels that for correlational studies in Chapter 2. For typical studies, sampling error causes error in treatment effects and causes studies to appear to be inconsistent with each other. If the usual analysis were based on confidence intervals, the large effects of sampling error would be recognized, and spurious differences between studies would be properly attributed ...