Scribd
Upload
344 views4 pages

Homework 4

This document describes an experiment conducted to analyze the effect of cotton percentage on tensile strength of synthetic fibers. Data from two experiments are presented: 1) An opera fundraising experiment tested three approaches and found a significant difference between the approaches based on a one-way ANOVA (p=0.001). 2) A fiber experiment tested five cotton percentages (15-35%), each replicated five times. A one-way ANOVA found cotton percentage affected mean tensile strength (p=0.000). Fisher's LSD method showed differences between all cotton percentage pairs.

Uploaded by

api-253978194
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
344 views4 pages

Homework 4

This document describes an experiment conducted to analyze the effect of cotton percentage on tensile strength of synthetic fibers. Data from two experiments are presented: 1) An opera fundraising experiment tested three approaches and found a significant difference between the approaches based on a one-way ANOVA (p=0.001). 2) A fiber experiment tested five cotton percentages (15-35%), each replicated five times. A one-way ANOVA found cotton percentage affected mean tensile strength (p=0.000). Fisher's LSD method showed differences between all cotton percentage pairs.

Uploaded by

api-253978194
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

IET 421/621*001 (Spring 2016)

Homework 4
Total Points: 10
Due date: 03/03/2016
Shane Holbrook
1. (5 points) A regional opera company has tried three approaches to solicit donations from 24
potential sponsors. The 24 potential sponsors were randomly divided into three groups of eight,
and one approach was used for each group. The dollar amounts of the resulting contributions are
shown in the following table.
Approach
1
2
3

1000
1500
900

Contributions (in $)
1200 1800 1600 1100
2000 1200 2000 1700
1200 1500 1200 1550

1500
1800
1000

1000
1800
1000

1250
1900
1100

(a) Do the data indicate that there is a difference in results obtained from the three different
approaches? Use = 0.05.
One-way ANOVA: C2 versus C1
Source
C1
Error
Total

DF
2
21
23

S = 269.1

SS
1362708
1520625
2883333

Level
1
2
3

N
8
8
8

Mean
1306.3
1737.5
1181.3

MS
681354
72411

R-Sq = 47.26%

F
9.41

P
0.001

R-Sq(adj) = 42.24%

Individual 95% CIs For Mean Based on Pooled StDev


-+---------+---------+---------+-------(-------*-------)
(-------*------)
(-------*-------)
-+---------+---------+---------+-------1000
1250
1500
1750

StDev
295.7
272.2
235.9

Pooled StDev = 269.1


Tukey 95% Simultaneous Confidence Intervals
All Pairwise Comparisons among Levels of C1
Individual confidence level = 98.00%
C1 = 1 subtracted from:
C1
2
3

Lower
92.6
-463.7

Center
431.2
-125.0

Upper
769.9
213.7

--------+---------+---------+---------+(------*-----)
(-----*------)
--------+---------+---------+---------+-500
0
500
1000

C1 = 2 subtracted from:
C1
3

Lower
-894.9

Center
-556.3

Upper
-217.6

--------+---------+---------+---------+(------*------)
--------+---------+---------+---------+-500
0
500
1000

From the MINITAB information above we can clearly see the p-value is 0.001, which is
less thean the level of significance which is 0.05. This clearly shows that we should
reject the null hypothesis of H0 and that there is a significant difference in the
approaches at the 5% level.

(b) Analyze the residuals from this experiment and comment on the model adequacy.
Residual Plots for C2
Normal Probability Plot

Versus Fits

99

500
Residual

Percent

90
50
10
1

250
0
-250
-500

-500

-250

0
Residual

250

500

1200

1350

4
3

250

2
1
0

1650

1800

Versus Order
500

Residual

Frequency

Histogram

1500
Fitted Value

0
-250
-500

-400

-200

0
Residual

200

400

8 10 12 14 16 18 20 22 24
Observation Order

From our Residual graph above we can clearly see the values are distributed as normal. Also from our
versus graph, we can see there are no signs of a problem and that the line is a good fit for the data. Also it
can be shown that the assumptions of analysis of variance are satisfied.

2.

(5 points) A product developer is investigating the tensile strength of a new synthetic fiber that
will be used to make cloth for mens shirts. Strength is usually affected by the percentage of
cotton used in the blend of materials for the fiber. The engineer conducts a completely
randomized experiment with five levels of cotton content and replicated the experiment five
times. The data are shown in the following table.
Cotton
Weight
Percentage
15
20
25
30
35

Observations
7
12
14
19
7

7
17
19
25
10

15
12
19
22
11

11
18
18
19
15

9
18
18
23
11

(a) Is there evidence to support the claim that cotton content affects the mean tensile strength? Use
= 0.05.
One-way ANOVA: Observations versus Cotton Weight Percent
Source
Cotton Weight Percent
Error
Total
S = 2.839

Level
15
20
25
30
35

N
5
5
5
5
5

DF
4
20
24

R-Sq = 74.69%

SS
475.76
161.20
636.96

Mean
9.800
15.400
17.600
21.600
10.800

StDev
3.347
3.130
2.074
2.608
2.864

MS
118.94
8.06

F
14.76

P
0.000

R-Sq(adj) = 69.63%
Individual 95% CIs For Mean Based on
Pooled StDev
------+---------+---------+---------+--(-----*----)
(----*----)
(----*----)
(----*----)
(-----*----)
------+---------+---------+---------+--10.0
15.0
20.0
25.0

Pooled StDev = 2.839


Fisher 95% Individual Confidence Intervals
All Pairwise Comparisons among Levels of Cotton Weight Percent
Simultaneous confidence level = 73.57%
Cotton Weight Percent = 15 subtracted from:
Cotton
Weight
Percent
20
25

Lower
1.855
4.055

Center
5.600
7.800

Upper
9.345
11.545

--------+---------+---------+---------+(----*----)
(----*---)

30
35

8.055
-2.745

11.800
1.000

15.545
4.745

(----*---)
(---*----)
--------+---------+---------+---------+-8.0
0.0
8.0
16.0

Cotton Weight Percent = 20 subtracted from:


Cotton
Weight
Percent
25
30
35

Lower
-1.545
2.455
-8.345

Center
2.200
6.200
-4.600

Upper
5.945
9.945
-0.855

--------+---------+---------+---------+(----*---)
(----*---)
(---*----)
--------+---------+---------+---------+-8.0
0.0
8.0
16.0

Cotton Weight Percent = 25 subtracted from:


Cotton
Weight
Percent
30
35

Lower
0.255
-10.545

Center
4.000
-6.800

Upper
7.745
-3.055

--------+---------+---------+---------+(----*----)
(----*---)
--------+---------+---------+---------+-8.0
0.0
8.0
16.0

Cotton Weight Percent = 30 subtracted from:


Cotton
Weight
Percent
35

Lower
-14.545

Center
-10.800

Upper
-7.055

--------+---------+---------+---------+(----*---)
--------+---------+---------+---------+-8.0
0.0
8.0
16.0

From this data from MINITAB the F-value is 14.76 and the p-value is 0.000, the p-value
is less than the level of significance of 0.05. Therefore we should reject the null
hypothesis H0 This simply means that the percentage of cotton in the fiber does effect the
mean tensile strength at 5%.
(b) Use the Fisher LSD method to make comparisons between the pairs of means. What conclusions
can you draw?
There is clearly a difference in all the percentages of cotton judging by the Fisher LSD
method test above in MINITAB.

You might also like