I am conducting a meta-analysis in which I am calculating the log OR and standart error of log OR form the extracted ORs and CIs in order to use the generic inverse variance method in RevMan. However, after entering the data to the software, the OR and CI output calculated by the software with generic inverse variance method is dissimilar to the original value extracted from the relevant study.
What does this mean? I checked my formulas and calculations,there seems to be no error. I also tried with MedCalc and get the same inconsistency.
I would very much appreciate your thoughts/suggestions.
Best,
Yusuf