Statistics 324 (Bates)
Midterm 2
20081113 (p. 1)
Choose the most appropriate answer. Mark only one selection. Use pencil.
1. In the test
H
0
:
μ
=
μ
0
vs.
H
a
:
μ > μ
0
with test statistic
t
obs
= (¯
x

μ
0
)
/
(
s/
√
n
) the pvalue
is (a)
P
[
T
n
< t
obs
] (b)
P
[
T
n
> t
obs
] (c) 2
·
P
[
T
n
>

t
obs

] (d)
P
[
T
n

1
< t
obs
] (e)
P
[
T
n

1
> t
obs
]
where
T
ν
denotes the T distribution with
ν
degrees of freedom.
2. When the pvalue for a hypothesis test is small, say 0
< p <
0
.
01, we
(a) reject
H
0
in favor of
H
a
(b) accept
H
0
(c) fail to reject
H
0
(d) reject
H
a
in favor of
H
0
(e) check our calculations because that value can’t occur
3. When the pvalue for a hypothesis test is large, say
p >
4
.
0, we
(a) reject
H
0
in favor of
H
a
(b) accept
H
0
(c) fail to reject
H
0
(d) reject
H
a
in favor of
H
0
(e) check our calculations because that value can’t occur
4. In a paired twosample ttest with
n
pairs of observed data values, the degrees of freedom for
the tstatistic are (a)
n

2 (b)
n

1 (c)
n
(d) 2(
n

1) (e) between
n

1 and 2(
n

1)
5. In an unpaired twosample ttest with
n
observations in each group, the degrees of freedom
for the tstatistic are (a)
n

2 (b)
n

1 (c)
n
(d) 2(
n

1) (e) between
n

1 and 2(
n

1)
6. If, in a normal probability plot for a single sample of data, the points fall approximately on
a straight line, then the slope of the line corresponds to (a) the sample standard deviation
(b) the sample variance (c) the sample mean (d) the sample median (e) the sample size .
7. In a statistical hypothesis test, the null hypothesis is
(a) a dimensionless statistic
(b) the probability of seeing the data that we did or something more unusual
(c) a claim about the parameters that we wish to establish
(d) a claim about the parameters that we wish to refute
(e) a claim about the parameters that is obviously true
8. The two possible conclusions in a statistical hypothesis test are (a) accept
H
0
or reject
H
a
(b) accept
H
0
or reject
H
0
(c) reject
H
0
(in favor or
H
a
) or do not reject
H
0
(d) accept
H
a
or reject
H
a
(e) do not reject
H
0
or do not reject
H
a
9. The pvalue in a test of
H
0
:
μ
= 6 versus
H
a
:
μ
6
= 6 is 0.0012. The value 6 will be included
in the (a) 0.1% (b) 1% (c) 95% (d) 99% (e) 99.9% conﬁdence interval.
10. To reach a deﬁnite conclusion (i.e. not a “no decision”) in a statistical hypothesis test, we
need the pvalue to be (a) large and negative, say less than 1000 (b) large and positive, say
greater than 1000 (c) near 1, representing certainty (d) near 0 but positive (e) near 0 and
either positive or negative
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentStatistics 324 (Bates)
Midterm 2
20081113 (p. 2)
The article “Promising quantitative nondestructive evaluation techniques for composite materials”
(
Materials Evaluation
This is the end of the preview.
Sign up
to
access the rest of the document.
 Fall '08
 Bates
 Statistics, Normal Distribution, Bates, Normal probability plot, neper/cm

Click to edit the document details