A Research Methodology to Conduct Effective Research Syntheses

Date

2014-01-01

Author

ÜSTÜN, ULAŞ
Eryılmaz, Ali

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

5
views

12
downloads

The need for comprehensive and systematic research syntheses has been increasing as the number of primary studies has proliferated in educational sciences in recent years. That is the main reason why diverse applications of meta-analysis, which is one of the most effective ways of research synthesis, has been encouraged in many disciplines including social and educational sciences. The main purpose of this article is to provide a conceptual framework for meta-analysis by questioning its criticisms and strengths over other methods of research synthesis. In addition, some methodological and statistical considerations like comparison of fixed-effect and random-effects models, different measures of effect size, unit of analysis, validity issues including publication bias and quality of primary studies, heterogeneity, moderator and power analyses in meta-analysis are discussed in detail. Moreover, brief information about software for statistical analyses performed in meta-analysis and a summary of standards for reporting meta-analysis are provided within the scope of this article. How well meta-analyses are conducted and reported is crucial since it has essential roles not only for cumulative nature of science but for policy makers and practitioners as well. Thus, we aim to provide the meta-analysts with an introductory-level guideline for their meta-analysis research.

Subject Keywords

Meta-Analysis , Research Synthesis , Effect Size , Moderator Analysis , Fixed-Effect Model , Random-Effects Model , Publication Bias

URI

https://hdl.handle.net/11511/40457

Collections

Department of Mathematics and Science Education, Article