Is it possible to calculate SMD when the only data reported is the mean scores before and at end of study, for intervention and control groups, along with significance levels?

This is how the data for the outcome I'm interested in is given in the paper. I am trying to calculate a common rubric for effect size.

                          Mean ± SD             Significance

                      Before      After

                    75.167.13*  66.326.55         p< 0.05
  • $\begingroup$ If by SMD you mean (Strictly) Standardized Mean Difference then you also need variances. $\endgroup$ – user2974951 Jan 30 '19 at 12:48
  • $\begingroup$ The study only reports SD for some outcomes (and not the ones I'm interested in) - I did think it wasn't possible to calculate the SMD without them - thank-you for helping. $\endgroup$ – Hello123 Jan 30 '19 at 12:53
  • $\begingroup$ Would there be any other way of calculating effect size with that data alone - I can't see any way but I'd like to be sure. $\endgroup$ – Hello123 Jan 30 '19 at 13:03
  • $\begingroup$ Can you include a table in your question with all the available data? $\endgroup$ – user2974951 Jan 30 '19 at 13:08
  • $\begingroup$ Have now edited question with data $\endgroup$ – Hello123 Jan 30 '19 at 13:39

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.