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.

Technical Questions in Meta-Analysis of Correlations

This chapter discusses technical questions that arise in the meta-analysis of correlations. These include the question of whether r or r2 should be used in meta-analysis, and the question of whether meta-analysis of regression slopes and intercepts is preferable to meta-analysis of correlations. Then we look at the Fisher's z transformation of r and show why it should not be used in meta-analysis. Next, this chapter discusses the important distinction between fixed and random models for meta-analysis and concludes that random models should always be used, as recommended by the National Research Council (1992). We then look at the literature on the accuracy of different random effects meta-analysis procedures. Then we discuss the distinction between credibility intervals ...

  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles