In: Statistics and Probability
The following data represent the muzzle velocity (in feet per second) of rounds fired from a 155-mm gun. For each round, two measurements of the velocity were recorded using two different measuring devices, resulting in the following data. Complete parts (a) through (d) below.
Observation |
1 |
2 |
3 |
4 |
5 |
6 |
|
---|---|---|---|---|---|---|---|
A |
794.4 |
790.8 |
794.1 |
794.1 |
791.8 |
790.4 |
|
B |
799.0 |
787.2 |
801.0 |
791.3 |
795.6 |
785.7 |
(a) Why are these matched-pairs data?
A.
The same round was fired in every trial.
B.
Two measurements (A and B) are taken on the same round.
C.
All the measurements came from rounds fired from the same gun.
D.
The measurements (A and B) are taken by the same instrument.
(b) Is there a difference in the measurement of the muzzle velocity between device A and device B at the
alpha equals 0.01α=0.01
level of significance? Note: A normal probability plot and boxplot of the data indicate that the differences are approximately normally distributed with no outliers.
Let
diequals=Aiminus−Bi.
Identify the null and alternative hypotheses.
Upper H 0H0:
mu Subscript dμd
▼
not equals≠
greater than>
equals=
less than<
nothing
Upper H 1H1:
mu Subscript dμd
▼
nothing
Determine the test statistic for this hypothesis test.
t0equals=nothing
(Round to two decimal places as needed.)
Find the P-value.
P-valueequals=nothing
(Round to three decimal places as needed.)
What is your conclusion regarding
Upper H 0H0?
▼
Upper H 0H0.
There
▼
is not
is
sufficient evidence at the
alphaαequals=0.010.01
level of significance to conclude that there is a difference in the measurements of velocity between device A and device B.
(c) Construct a 99% confidence interval about the population mean difference. Compute the difference as device A minus device B. Interpret your results.
The lower bound is
nothing.
The upper bound is
nothing.
(Round to two decimal places as needed.)
Interpret the confidence interval. Choose the correct answer below.
A.
One can be 1% confident that the mean difference in measurement lies in the interval found above.
B.One can be 99% confident that the mean difference in measurement is
0.010.01.
C.
One can be 99% confident that the mean difference in measurement lies in the interval found above.
D.
One can be 99% confident that the mean difference in measurement is 0.
d) Draw a boxplot of the differenced data. Does this visual evidence support the results obtained in part (b)?
A.
-8-6-4-20246Differences
x y graph
B.
-8-6-4-20246Differences
x y graph
C.
-8-6-4-20246Differences
x y graph
D.
-8-6-4-2024Differences
x y graph
Does this visual evidence support the results obtained in part (b)?
A.Yes, because 0 is
containedcontained
in the boxplot.
B.
Yes, because the boxplot shows no outliers.
C.
No, because the boxplot is too large.
D.No, because 0 is
not containednot contained
in the boxplot.
Given that,
null, H0: Ud = 0
alternate, H1: Ud != 0
level of significance, α = 0.01
from standard normal table, two tailed t α/2 =4.032
since our test is two-tailed
reject Ho, if to < -4.032 OR if to > 4.032
we use Test Statistic
to= d/ (S/√n)
where
value of S^2 = [ ∑ di^2 – ( ∑ di )^2 / n ] / ( n-1 ) )
d = ( Xi-Yi)/n) = -0.7
We have d = -0.7
pooled variance = calculate value of Sd= √S^2 = sqrt [
126.1-(-4.2^2/6 ] / 5 = 4.963
to = d/ (S/√n) = -0.345
critical Value
the value of |t α| with n-1 = 5 d.f is 4.032
we got |t o| = 0.345 & |t α| =4.032
make Decision
hence Value of |to | < | t α | and here we do not reject
Ho
p-value :two tailed ( double the one tail ) - Ha : ( p != -0.3455 )
= 0.7438
hence value of p0.01 < 0.7438,here we do not reject Ho
ANSWERS
---------------
a.
matched-pairs data because both dependent variables
b.
null, H0: Ud = 0
alternate, H1: Ud != 0
test statistic: -0.345
critical value: reject Ho, if to < -4.032 OR if to >
4.032
decision: Do not Reject Ho
p-value: 0.7438
we do not have enough evidence to support the claim that difference
in the measurement of the muzzle velocity between device A and
device B
c.
Confidence Interval
CI = d ± t a/2 * (Sd/ Sqrt(n))
Where,
d = ∑ di/n
Sd = Sqrt( ∑ di^2 – ( ∑ di )^2 / n ] / ( n-1 ) )
a = 1 - (Confidence Level/100)
ta/2 = t-table value
CI = Confidence Interval
d = ( ∑ di/n ) =-4.20000000000016/6=-0.7
Pooled Sd( Sd )= Sqrt [ 126.1- (-4.2^2/6 ] / 5 = 4.963
Confidence Interval = [ -0.7 ± t a/2 ( 2.865/ Sqrt ( 6) ) ]
= [ -0.7 - 4.032 * (2.026) , -0.7 + 4.032 * (2.026) ]
= [ -8.869 , 7.469 ]
d.
-8-6-4-20246 Differences
x y graph
A.
Yes, because 0 iscontained in the boxplot.