Hypothesis Testing Part II
Steel and Torrie
Ho: uo=o is the null hypothesis
HA: uo
o is
the alternative hypothesis
| Decision
Relative To |
| Ho
is |
HA
is |
Ho
is |
HA
is |
Decision
is |
| True |
False |
Accept |
Reject |
Right |
| True |
False |
Reject |
Accept |
Wrong:Type
I |
| False |
True |
Accept |
Reject |
Wrong:Type
II |
| False |
True |
Reject |
Accept |
Right |
When we erroneously reject Ho when Ho is true, this is a Type I error.
An alternative type of error would be to accept Ho when it is actually
false and this would be a Type II error.
We might make the mistake of rejecting Ho when it is true because of
an unusual sample. The sampling process will occasionally result in
an unusual sample that has a large deviation from the expected proportion.
Distribution of means when HO is true.
| The
probability of a sample with the mean U1 or
greater when the true Mean is U0. |
The
probability of a sample with the mean U1 or
greater when the true Mean is U0. |
