In order to conduct power analysis for a T-test, you need to have a value of the expected effective difference (effect size) between the two sample means that you wish to detect.

The formula for effect size (Cohen's d statistic) is:

\[d={\frac {{\bar {x}}_{1}-{\bar {x}}_{2}}{s}}\] Where \({\bar {x}}\) are sample means and \({s}\) is the pooled standard deviation whose formula is given below.

\[s={\sqrt {\frac {(n_{1}-1)s_{1}^{2}+(n_{2}-1)s_{2}^{2}}{n_{1}+n_{2}-2}}}\] Where \({n}\) and \({s}\) are the sample sizes and standard deviations respectively.

Remember to use this formula to calculate the variances for each sample. \[s_{1}^{2}={\frac {1}{n_{1}-1}}\sum _{i=1}^{n_{1}}(x_{1,i}-{\bar {x}}_{1})^{2}\] To go back to my power analysis app click here.

For more information about effect size check out Wikipedia.