|
Hypothesis Testing (Four Steps)
Step 1:
Translate the claim into a
hypothesis statement. Assign the claim to one of the following
symbols:
=, , >
, <, < , >.
Label either the Null Hypothesis, H0, or the Alternate Hypothesis, H1, as the
claim.
Choose from one of the following three scenarios.
Case
1
H0: µ = #
H1: µ #
|
 |
Case
2
H0: µ > #
(or H0: µ = #)
H1: µ < #
|
 |
Case
3
H0: µ < #
(or H0: µ = #)
H1: µ > #
|
 |
Each case is an unbreakable package.
The symbols,
=, , >
, <, < , >, cannot be combined in any other combination or
with different diagrams.
Step 2:
Use the level of significance, ,
to determine the size (area) of the "Reject H0"
region.
If H0 = #,
then the size (area) of each "Reject H0" region is
/ 2. Label on
the diagram.
Note: The level of significance is usually given as part of
the problem. In situations
where it is not provided,
use = 0.05 as the
default value.
Note: In problems (tests of the standard deviation) where
your calculator does not
have the appropriate program, a
critical value, a value read from the
appropriate table, will separate the "Reject H0"
region from the "Fail
to
Reject H0" region.
Step 3:
Use your calculator and
the appropriate test to
calculate the test statistic and
its corresponding p value. The test
statistic is used to determine
which test to run. The p value is the
probability of the sample happening given that the Null
Hypothesis is
true. For each case, the p value is:
For Case 1 (H0 = #): Twice the area to the left
of a
negative z-score or twice the area to
the right of a positive z
score.
For Case 2 (H0 > #): The area to the left of the
z
score.
For Case 3 (H0 < #): The area to the right of the z
score.
On the diagram, compare the p
value to the level of significance.
If the p value falls within the "Reject H0" region,
then reject the Null Hypothesis, H0.
Note: In problems (tests of the standard deviation) where
your calculator does not have
the appropriate program, a
test statistic, a value
calculated from a formula,
will be
found. If the p value falls within the "Reject H0"
region,
then reject the
Null Hypothesis, H0.
Step 4:
Make two statements.
1.
Did you "Reject" or "Fail to Reject" the Null
Hypothesis, H0.
2. Does the data appear to support or refute
the claim? |