Meta-analysis is arguably the most important methodological innovation in the social and behavioural sciences in the last 25 years. This revision of Hunter and Schmidt's book, Methods of Meta-Analysis (SAGE 1990), covers the important new developments in meta-analysis methods over the last 14 years. This edition presents an evaluation of fixed versus random effects models for m...
Meta-analysis is arguably the most important methodological innovation in the social and behavioural sciences in the last 25 years. This revision of Hunter and Schmidt's book, Methods of Meta-Analysis (SAGE 1990), covers the important new developments in meta-analysis methods over the last 14 years. This edition presents an evaluation of fixed versus random effects models for meta-analysis, new methods for correcting for indirect range restriction in meta-analysis, new developments in corrections for measurement error (including how to select the appropriate reliability coefficients to use), a discussion of a new Windows-based program package for applying the meta-analysis methods presented in the book, and a discussion of the theories of data underlying different approaches to meta-analysis. Coverage of these topics along with updated coverage of many other topics makes this book the most comprehensive text on meta-analysis methods available today.
原文摘录
· · · · · ·
This section also presents the mathematics of a meta-analysis in which sampling error is the only artifact corrected. Alas, there are those who do not believe that other artifacts exist. There are also those who believe that if there are artifacts in the original study, then those same srtifacts should be reflected in the meta-analysis. They believe that the purpose of meta-analysis is only to describe observed results and that meta-analysis should not correct for known problems in research design. However, most scientists believe that the goal of cumulative research is to produce better answers than can be obtained in isolated studies. From that point of view, the purpose of meta-analysis is to estiamte the relationships that would have been observed if studies had been conducted perfectl... (查看原文)
0 有用 咩咩得意 2013-12-28 19:33:14
好书啊！！比老师讲得好多了
0 有用 草履猴 2015-11-29 04:59:14
元分析研究必备