17.9.3.2 Algorithms ((PSS) Paired-Sample t-Test)

For given degree of freedom $\nu =n-1\,\!$ and $s\,\!$ standard deviation , the Power for paired sample t-Test is calculated by:

$Power=Prob(t >t_{(1-\alpha ,\nu )},\nu ,\lambda )\,\!$

for one-sided test and

$Power=Prob(t >t_{(\alpha /2,\nu )},\nu ,\lambda )+Prob(t>t_{(1-\alpha /2,\nu )},\nu ,\lambda )\,\!$

for a two-sided test.

Where the noncentrality parameter: $\lambda =\delta \sqrt{n} \,\!$ and $\delta =\frac{\left| \mu _1-\mu _2\right| }s\,\!$

English | Deutsch | 日本語