One Sample Hypothesis Testing
One Sample Hypothesis Testing
One Sample Hypothesis Testing
X
z
X
N
X
z
X
z
N
X
z
2
, the sampling distribution of the mean (the
distribution of sample means) will have a
mean equal to (i.e., = ) and a variance
(
2
) equal to
2
/N (and standard deviation,
= /N). The distribution will approach the
normal distribution as N, the sample size,
increases.
X
X X
Hypothesis Testing w/ One
Sample
Example #1:
You want to test the hypothesis that the current
crop of Kent State freshman are more depressed
than Kent State undergraduates in general.
What is your sample and what is your population?
What is your H
o
and your H
1
?
Are you using a one- or two-tailed test?
Assuming that for current Kent State freshman, their
mean depression score is 15, while the mean for all
previous Kent State undergrads (N = 100,000) is 10,
and their standard deviation is 5
Hypothesis Testing w/ One
Sample
= 5/.0158 = 316.46
Look up value in Table E10 with value in Smaller
Portion
p < 0.0000
Since this is less than .05 (or .025 if we were using a
two-tailed test), we could conclude that the current
batch of freshman is significantly more depressed
than previous undergrads
Also notice the effect that our large N had on our p-value
000 , 100
5
10 15
z
Hypothesis Testing w/ One
Sample
Example #2:
You want to test the hypothesis that a treatment conducted
at the ward you are working on in a hospital is more
beneficial than the average treatment used in other wards
of the hospital
Get into groups of 2 or more
State H
o
and H
1
State if youre using a one- or two-tailed test and why.
Given that the mean wellness score of the people on your
ward is 87, and that the mean for the entire hospital (N =
20) is 76 and the standard deviation is 15, is your ward
significantly better? State the p-value that supports your
claim.
Hypothesis Testing w/ One
Sample
Example #2:
= 11/3.36 = 3.27
Smaller Portion = p < .0006
20
15
76 87
z
Hypothesis Testing w/ One
Sample
Most often, however, we dont know the and ,
because this is what were trying to estimate with
our sample in the first place
The formula for the t statistic accomplishes this by
substituting s
2
for
2
in the formula for the z statistic
Because of this substitution, we have a different
statistic, which requires that we use a different table
than E.10
Dont worry too much about why its different (you
can skip pg. 274 in your book if you want, you wont
be tested on it)
Hypothesis Testing w/ One
Sample
Testing mean versus
standard deviation for
distribution of sample
means
I.e. standard error
Testing mean versus
standard deviation for
sample
N
s
X
t
N
X
z