Reviewing The Evidence Flashcards
What is meta-analysis?
It is “a quantitative synthesis of the results of two or more primary studies that addressed the hypothesis in the same way”
What is the purpose of a meta-analysis?
To quantify effect sizes and their uncertainty as a pooled estimate. By pooling studies you reduce the size of the confidence intervals.
When doing a meta-analysis studies are weighted. What would give a greater weighting? (3)
The size of the study, the uncertainty of their odds ratio and how small their error factor is
In a Forest plot the size of a square is proportional to…..
The weight given to that particular study
What does the diamond represent on a forest plot?
It represents the pooled estimate
What does the vertical dotted line represent on a forest plot?
It represent the pooled odds ratio
What does the diamond’s width represent on a forest plot?
The pooled confidence interval
What does the solid vertical line represent on a forest plot?
It represents the null hypothesis odds ratio
What are the two models for calculating the pooled odds ratio and confidence interval?
The fixed effect model and the random effects model. They both model for variation and account for heterogeneity
Which model allows for decreased heterogeneity? And no would you check which model was used?
The random effects model is better and you would check using a forest plot
How do you try an explain heterogeneity between studies?
Sub-group analysis
What are the two types of sub-group analysis?
- Stratification by study characteristics
- Stratification by participant profile
What is publication bias?
Studies with statistically significant or “favourable” results are more likely to be published. This affects systematic reviews
How do you identify publication bias?
Either:
- Check meta-analysis protocol for method of identification of studies
- A funnel plot
- Use a statistical test
What is a funnel plot?
It compares results of identified studies against a measure of their size
