The mean and SD are for glucose levels.
The only data provided is mean +- SD for each of these groups, without individual values. the n of each group is available.
Is there a statistical way to calculate a mean +- SD for N (total males in both groups)? Thanks
Yes, this is easy to do to provide a new mean and standard deviation for the summed number of individuals. The computer does this easily. For example see: http://www.statstodo.com/ComMeans_Pgm.php
As Helena hints, the issue is whether it's reasonable or not to combine these sets. A good reference here is "The Flaw of Averages" by Sam Savage. For example combining proportions by % of men < 20 and >70 with prostate cancer does not produce 'an average prostate cancer %' for the male population that is statistically valid.
Thank you so much Helena and Alan for your tremendously helpful reply. I am very appreciative.
warm regards
Fateh
I agree with the answers of both Helena and Alan (reply a little late, but better late than never). I needed to use this before in the context of a meta-analysis (table-1 data), so I pooled them as continuous variables (aka, weighted mean and SD). I've used the formula found in the Cochrane handbook for that purpose. Happy to point out where it is if needed.
Good luck, Fateh.
- Badges
- Science topic