for example: its a comparison study, and each time control group is same but test group is different.
Not in a standard meta-analysis, because it will 'double-count' the participants.
If you have studies with 2 or more comparisons (a vs b, b vs c) you may need to conduct a network meta-analysis.
It is imperative to divide the participants in the control group by the number of rows entered for each test; otherwise, the participants in the control group would be included in the analysis multiple times. The unrealistic increase in sample size results in a false conclusion. Aimen Batool
I agree with Dr. Noormohammadi. Split the control group or combine the groups using the formula provided by the Cochrane Collaboration:
https://handbook-5-1.cochrane.org/chapter_7/table_7_7_a_formulae_for_combining_groups.htm
Hello Aimen Batool
I agree with Joseph Whittaker - trust the Josephs to stick together (!) - that the people cannot be duplicated because it simply makes your calculation(s) flawed. I would suggest, instead, that the two questions be separated and answered independently. You might want to do it in two separate papers or combine the questions and with them individually in one publication - that would be up to you and the data/size you are investigating.
- Badges
- Science method
- Similar topics
- Methodology