I am collecting data on the effect calorie labeling has. Each study provides a value for mean calories consumed before the calorie label and after. Each number has a standard error or deviation associated with it. I want to combine multiple studies and calculate a mean percentage change with a standard error value. How would I go about this? Thanks for reading

  • 1
    $\begingroup$ You can use the post intervention means and SD. You can also calculate the change score (and SD). The formula is in the Cochrane Handbook. You won't be able to calculate the % change from baseline with the reported results; you would need the individual patient data for that. I would say just use the post intervention means and SDs. $\endgroup$
    – abousetta
    Apr 20 at 19:48
  • $\begingroup$ Thanks for the reply! I'll try that $\endgroup$
    – nomad
    Apr 21 at 16:28


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.