I'm doing a meta-analysis for continous outcomes and most of the data from the studies is reported as median, IQR (as difference Q3-Q1), I already know Wan (2014) method and McGrath (2021) method, but those only are appliable when the exact values of the quartiles are available, I was thinking about using IQR/1.35 to get the SD and asume a normal distribution so the median=mean, and then try a sensitivity analysis to evaluate the effect of using those studies as presented.
Hi Raid Amin. As I understood it, Mariano Gallo Ruelas has no raw data for any of the studies. For many of them, he has only the median and Q3-Q1, but not the values of Q1 and Q3. And as I understood it, the two possible approaches he mentioned (Wan 2014; McGrath 2021) require the exact values of Q1 and Q3, not just the difference between them.
Mariano Gallo Ruelas, I have no firsthand experience with the problem you described, but a Google search took me to the documentation for this R-package:
https://cran.r-project.org/web/packages/metamedian/metamedian.pdf
Notice that some more articles are mentioned in the Description section. Some of them may be helpful. See also the Reference list.
HTH.
Yes, Cochrane calculator uses confidence intervals to obtain standard deviations, but under the assumption that the mean=median. I also encountered a formula to get the quartiles such as Q1= Median - IQR/2 and Q3=Median+IQR/2, but I cannot find an official reference to cite that method.
- Badges
- Science topic
- Similar topics
- Phytochemistry
- Extracts