521 / 762
Chapter 12: Hypothesis Tests – Large Samples
521
Summary of Hypothesis Tests
(a) Right –tailed (one-tailed) Test
(where
is a specified proportion value)
√
: For a specified significance level
, reject the null hypothesis
if the computed test statistic value
z
is greater than +
z
.
Conclusion
: ……….
Notes
:
1.
This is a right-tailed test because the direction of the inequality sign in
is to the right.
2.
This test falls under the category of the
classical approach
to
hypothesis testing because we will be comparing a test statistic value
to a critical value from a probability distribution.
3.
Recall that the null hypothesis states that there is no difference
between a parameter (or parameters) and a specified value. This
means we should use an equal sign in the statement of the null
hypothesis. However, instead of the equal sign we will use the
equivalent complement symbol which is used in the alternative
hypothesis.
4.
For instance, if we have “>” in the alternative hypothesis, then we will
use the complement symbol “
” in the null hypothesis. This does not
change the definition of the null hypothesis because during the
hypothesis test we assume that the null hypothesis is true and we test
at the “=” sign. That is, we will assume that the parameter is equal to
the specified value during the test procedure.