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:

  • For a Greater than Alternative Hypothesis:

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


  • For a Less than Alternative Hypothesis:

Power=Prob(t <t_{(\alpha ,\nu )},\nu ,\lambda )\,\!


  • For a Not Equal Alternative Hypothesis:

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


Where the noncentrality parameter:

\lambda =\delta \sqrt{n} \,\!

and

\delta =\frac{ \mu _\alpha -\mu _0 }s\,\!

English | Deutsch | 日本語