# Can I obtain the means for two groups using their mean difference?

I have a study which provides the mean difference for two groups (alongside 95%CI, SE, n and p-value). I would like to extrapolate the raw means to use in Revman to perform a random-effect SMD meta-analysis. Can I extrapolate the raw means from the MD?

• Do you have either of the group means? – gung - Reinstate Monica May 2 '16 at 14:27
• Nope, paper doesn't give them sadly – samleighton87 May 2 '16 at 14:48

This is tantamount to asking whether, if you knew $x + y = 20$, can you identify $x$ and $y$ uniquely. The answer is, of course, no. There are infinitely many possible solutions.