Hi,

The best resource on this topic is the Cochrane Handbook for Systematic reviews of Interventions - Chapter 16.4.

To quote from the sub-chapter 16.4.5: Methods for incorporating cross-over trials into a meta-analysis

"Unfortunately, the reporting of cross-over trials has been very variable, and the data required to include a paired analysis in a meta-analysis are often not published. A common situation is that means and standard deviations (or standard errors) are available only for measurements on E and C separately. A simple approach to incorporating cross-over trials in a meta-analysis is thus to take all measurements from intervention E periods and all measurements from intervention C periods and analyse these as if the trial were a parallel group trial of E versus C.  This approach gives rise to a unit-of-analysis error (see Chapter 9, Section 9.3) and should be avoided unless it can be demonstrated that the results approximate those from a paired analysis, as described in Section 16.4.4. The reason for this is that confidence intervals are likely to be too wide, and the trial will receive too little weight, with the possible consequence of disguising clinically important heterogeneity. Nevertheless, this incorrect analysis is conservative, in that studies are under-weighted rather than over-weighted. While some argue against the inclusion of cross-over trials in this way, the unit-of-analysis error might be regarded as less serious than some other types of unit-of-analysis error.

A second approach to incorporating cross-over trials is to include only data from the first period. This might be appropriate if carry-over is thought to be a problem, or if a cross-over design is considered inappropriate for other reasons. However, it is possible that available data from first periods constitute a biased subset of all first period data. This is because reporting of first period data may be dependent on the trialists having found statistically significant carry-over.

A third approach to incorporating inappropriately reported cross-over trials is to attempt to approximate a paired analysis, by imputing missing standard deviations. We address this approach in detail in Section 16.4.6.

Cross-over trials with dichotomous outcomes require more complicated methods and consultation with a statistician is recommended (Elbourne 2002)"

I hope this helps. You can contact me through e-mail if you need more help.

Best

Jeeva  

Sample size estimations are employed for individual trials for preventing type I or II errors.. That is to say for detecting an existing treatment contrast between Drug A vs Drug B we should have at least %85 chance to detect that significance.. With aplha let's say 0.05 and estimated effect sizes for each of Drug A vs B we compute an ideal sample size  for that trial. However, for a study level meta-analysis our subjects are trials now and we consider number of trials included rather than number of subjects per trial arm as we think of stregth of our findings.. So cross-over or not n per trial arm is not a matter we should consider for conducting a meta-analysis.

Dear Ayşegül Yildiz,

I agree with your explanation that its the number of studies are more important than sample size in individual studies while doing meta-analysis. But, while you carry out meta-analysis (Forrest Plot) weightage of study depends on its Sample size and Variation in each study. Hence sample size of each study have some role to play in meta-analysis. 

So my fundamental question is what should be the sample size for each intervention ?

Regards

Dear Jeeva Sankar,

Sir, thank you for sharing the valuable information.

I may need your assistance, so please drop your email ID.

Regards