standardized mean difference vs raw mean difference Is there a difference between standardized mean difference and raw mean difference when conducting meta analysis or systematic review  and the measurement scales are same, would SMD and raw mean difference be the same ?    
 A: The purpose of using SMD is to uniform scale before they are combined. So if you already have same measurement scale, SMD is not necessary. According to this Cochrane page, the standardized mean difference is used as a summary statistic in meta-analysis when the studies all assess the same outcome but measure it in a variety of ways (for example, all studies measure depression but they use different psychometric scales). In this circumstance it is necessary to standardize the results of the studies to a uniform scale before they can be combined. The standardized mean difference expresses the size of the intervention effect in each study relative to the variability observed in that study. 
A: It is best to base your decision on the underlying science of the problem. If the scales are different then clearly you have no choice but to use a standardised measure. If they are the same then the advantage of the weighted mean difference over the standardised one is that the summary is reported on the original scale and so will be more understandable to your audience. You need to be careful though that the scales are genuinely the same. For instance suppose each study has compared the salaries of men and women in euros. If the studies had taken place in very different environments so there were big differences in salaries between studies you might still want to standardise here even though one euro is one euro everywhere because you might feel that a difference between men and women of 1000 euro is more important in a low salary environment than a high salary one. You could argue both ways here but the important thing is to pick the method which corresponds to your scientific question.
