I have performed a pilot study comparing the means of two groups and I've yielded non-significant results. I wish to determine whether increasing the sample size would have produced a significant difference. My means and SD are:

Group 1: mean = 0.086
         SD = 0.05524
         ( n = 5)

Group 2: mean = 0.0926
         SD - 0.0509

What is the best formula to use to consider what sample sizes would render these results significant?

  • $\begingroup$ What statistical test did you use? This is important to determine the sample size. Given the observed mean difference and its variability, it is unfortunately no surprise to arrive at a non-significant result with these group sizes. $\endgroup$ – ocram Apr 14 '15 at 19:05
  • $\begingroup$ Hi. I performed an unpaired t-test $\endgroup$ – Kim Apr 14 '15 at 19:07
  • $\begingroup$ stats.stackexchange.com/questions/37993/… $\endgroup$ – ocram Apr 14 '15 at 19:10

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.