Meta-Analysis

Meta-analysis is a structured literature review technique that attempts to combine similar studies to determine the average effect size for a particular treatment under comparable circumstances with comparable participants.

Meta-analysis is all about putting the different pieces of the puzzle together in a scientific way. It combines the findings of many different studies using statistical methods. These studies offer a real, quantifiable sense of where the evidence is leading.

Cumulative Evidence

Cumulative evidence is another method used to look at the big picture. Rather than using a complex mathematical model, though, cumulative evidence simply means stacking up all the related studies and figuring out what they say overall.

Think of a fictional detective looking at fingerprints, eyewitness testimony, DNA evidence, and circumstantial evidence, and putting them all together to see what kind of case they build.

Image courtesy of American Institute of Cancer Research

Meta-analysis can be used as a guide to answer the question:

'Does what we are doing make a difference to X' even if 'X' has been measured using different instruments across a range of different people?

Meta-analysis provides a systematic overview of quantitative research that has examined a particular question.

Advantages of meta-analysis: It combines all the research on one topic into one large study with many participants.

Disadvantage: The danger is that in combining a large set of different studies the construct definitions can become imprecise and the results difficult to interpret meaningfully.

Steps in a meta-analysis

1. Search of literature

2. Selection of studies ('incorporation criteria')

• Based on quality criteria, e.g. the requirement of randomization and blinding in a clinical trial.
• Selection of specific studies on a well-defined subject, e.g. the treatment of breast cancer.
• Decide whether unpublished studies can be included to avoid publication bias. (file drawer problem)

3. Decide which dependent variables or summary measures are allowed in the comparison.

4. Statistical model selection

5. Reporting