Lecture 30: Interpreting Meta Analysis

Question 1

define meta analysis

Answer 1

“The statistical synthesis of the data from separate but similar (i.e., comparable studies) leading to a quantitative summary of the pooled
results”

Question 2

what does a forest plot show? (2)

Answer 2

– Information from the individual studies that went into the meta analysis
– Amount of variation in treatment effect between studies
- how much each study contributed to overall result
- shows estimate of OVERALL result

Question 3

what type of outcomes are possible for Pooled Estimate on Dichotomous Outcomes?

Answer 3

• Relative Risk
• Relative Risk Reduction
• Odds Ratio
• Hazard Ratio

Question 4

what type of outcomes are possible for Pooled Estimate on continuous Outcomes?

Answer 4

• Weighted Mean Difference

* Standardized Mean Difference

Question 5

see examples of diff plots

Answer 5

ok

Question 6

benefit of a meta analysis?

Answer 6

By pooling the results of multiple studies in a meta-analysis, you # the absolute
number of events, which in turn makes the confidence intervals more precise and
increases your confidence in the estimate of treatment effect.