For example I have some studies that measure effect size in mm2 (Area) and studies that measure it in mm (Diameter), both studies measure the same object. Also, studies measure it at slightly different sites in the body. My main objective of this meta analysis is to see if there is a significant difference between patients and controls regarding the size of this object. How should I deal with the difference in measuring scales?
Thank you for the answers, but the outcome is measured by a different scale across studies with a different unit. Shouldn't standardized mean difference be more appropiate here?
It certainly sounds like you need to used SMD. The Cochrane Handbook is exceptionally useful for matters like this if you haven't yet come across it.
Here is the chapter discussing SMD:
https://handbook-5-1.cochrane.org/chapter_9/9_2_3_2_the_standardized_mean_difference.htm
Good luck!
I changed my opinion, I think SMD is more appropriate due to different scales
I suppose from what I have understood that SMD, in this case, is more appropriate since the outcome of interest is measured using different scales and different units.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Meta-Analysis