Meta Ananlysis

Meta –analysis is a method which can be used to combine the results of two or more studies. The first Meta –analysis performed by karlpearson in 1904

Meta –analysis may conveniently be defined as a quantitative method of pooling information from independent studies concerning a single theme in order to draw conclusion.

Meta –analysis does not simply involve averaging the results of the individual studies, but requires a statistical method which combines the result whilst taking into account the size of the studies. Thus Meta –analysis is the statistical analysis of a large collection of analysis results for the purpose of integrating the findings.

Meta –analysis can provide researchers with single pooled results to answer whether treatment A is more beneficial than treatment B. This pooled result is usually more precise than the result from the individual studies. The precision with each of these studies calculates the treatment effect depends on many factors including the number of people in the study. Generally as the number of people increases in a study the precision of the treatment effect will increase.

Therefore by statistical combining the all the sample size together from the individual studies, the precision of our pooled result for the treatment effect can be improved.

Meta – analysis increases power. By combining the results from the smaller studies using Meta– analysis we can increase the overall power of the analysis. Therefore, the results from a Meta – analysis will usually have more power than the results from the individual studies.

STEPS TO PERFORM META – ANALYSIS

The theoretical  relationship of interest

Collect the population of studies that provide data on the relationship.

Code the studies and compute the effect sizes

Examine the distribution of effect sizes and analyze the impact of moderating variables

Interpret and report the results.

SUMMARY

 Meta – analysis leads to a shift of emphasis from single studies to multiple studies. It is performed with assistance of computer data bases (Microsoft access, paradox) and statistical software (DSTAT, SAS). The most common use of Meta – analysis has been in quantitative literature review. A valid meta – analysis however, require careful planning in the protocol stage as for any other research.