Hypothesis Testing The z-test for Proportions
Hypothesis Testing The z-test for Proportions
Hypothesis Testing The z-test for Proportions
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
α<br />
<strong>The</strong> Test Statistic<br />
pˆ<br />
− p<br />
z =<br />
σ<br />
Reject H0<br />
0<br />
=<br />
pˆ<br />
− p<br />
p<br />
( 1−<br />
p )<br />
pˆ 0 0<br />
n<br />
<strong>The</strong> Acceptance region:<br />
− zα<br />
0<br />
0 z<br />
Accept H0 Comments<br />
• <strong>The</strong> alternative <strong>Hypothesis</strong> (H A) is<br />
what the experiment is trying to<br />
prove - the Research <strong>Hypothesis</strong><br />
• <strong>The</strong> alternative <strong>Hypothesis</strong> (H A) will<br />
determine if you use a one-tailed <strong>test</strong><br />
or a two tailed <strong>test</strong><br />
• If you are trying to prove a difference<br />
H A<br />
: p ≠ p<br />
• This is the alternative <strong>Hypothesis</strong> (H A)<br />
- the Research <strong>Hypothesis</strong><br />
• Use a two tailed <strong>test</strong><br />
• If you are trying to prove the true value p<br />
exceeds the hypothesized value p 0<br />
H A<br />
: p > p<br />
• This is the alternative <strong>Hypothesis</strong> (H A)<br />
- the Research <strong>Hypothesis</strong><br />
• If you are trying to prove the true value p<br />
does not exceed the hypothesized value p 0<br />
H A<br />
: p <<br />
p<br />
• This is the alternative <strong>Hypothesis</strong> (H A)<br />
- the Research <strong>Hypothesis</strong><br />
0<br />
0<br />
0<br />
3