Can anyone provide with some advice? - thank you

I am required to calculate the sample size for two groups, given the following data:

Total sample N (group1+group2)=583

group 1: mean=8.35, SD1.07, N1=?

group 2: mean=8.11, SD1.32, N2=?

In case this extra infomation is useful: The total of N=583 subjects answered a 12-item questionnaire. Each item was scored on a scale of 1-10: 1=very poor, 10=excellent. The p-value between the two groups: p=0.02

  • 2
    $\begingroup$ Then N = 583... :-) More seriously, I suggest you explain more carefully what your setting is, at present what the question is is quite unclear. $\endgroup$ – Did Nov 24 '12 at 10:58
  • $\begingroup$ Thank you for reading my post, I have edited my question and I hope it makes more sense now. $\endgroup$ – user50505 Dec 1 '12 at 0:19

I asked a very similar question only yesterday. If your samples are homoscedastic (can be assumed if subjects are randomly chosen) you can estimate the variance to behave reciprocally to sample size.

$\sigma^2 \propto \frac{1}{N} \Rightarrow N \propto \frac{1}{\sigma^2} \Rightarrow N_1=\frac{\frac{1}{1.07^2}}{\frac{1}{1.07^2} + \frac{1}{1.32^2}} * 583 \approx 352$


Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.