How to avoid data dredging in this situation?
I'm conducting a complicated meta-analysis of animal studies with multiple comparisons in each study.
I can solve the heterogeneity by sensitivity and subgroup but the results are not meaningful.
And I can perform another meaningful sensitivity and subgroup analysis but with serious heterogeneity.
What is the priority here.
Best regards,
Andrew Paul McKenzie Pegman
You can use a random effects model instead. It is a hierarchical linear model, which assumes that the data being analysed are drawn from a hierarchy of different populations whose differences relate to that hierarchy.
0 votes
0 thanks
- Badges
- Science topic
More Osama Abunar's questions See All
Similar questions and discussions