You are on page 1of 11

STAT 503, Fall 2005

Homework Solution 2

Due: Sept. 15, 2005

3-1 The tensile strength of portland cement is being studied. Four different mixing techniques can be
used economically. The following data have been collected:
Mixing
Technique
1
2
3
4

3129
3200
2800
2600

Tensile Strength (lb/in2)


3000
2865
3300
2975
2900
2985
2700
2600

2890
3150
3050
2765

(a) Test the hypothesis that mixing techniques affect the strength of the cement. Use = 0.05.
Design Expert Output
Response:
Tensile Strengthin lb/in^2
ANOVA for Selected Factorial Model
Analysis of variance table [Partial sum of squares]
Sum of
Mean
Source
Squares
DF
Square
Model
4.897E+005
3
1.632E+005
A
4.897E+005
3
1.632E+005
Residual
1.539E+005
12
12825.69
Lack of Fit
0.000
0
Pure Error
1.539E+005
12
12825.69
Cor Total
6.436E+005
15

F
Value
12.73
12.73

Prob > F
0.0005
0.0005

significant

The Model F-value of 12.73 implies the model is significant. There is only
a 0.05% chance that a "Model F-Value" this large could occur due to noise.
Treatment Means (Adjusted, If Necessary)
Estimated
Standard
Mean
Error
1-1
2971.00
56.63

2-2 3156.25
3-3 2933.75
4-4 2666.25
Treatment
1 vs 2
1 vs 3
1 vs 4
2 vs 3
2 vs 4
3 vs 4

Mean
Difference
-185.25
37.25
304.75
222.50
490.00
267.50

56.63
56.63
56.63
DF
1
1
1
1
1
1

Standard
Error
80.08
80.08
80.08
80.08
80.08
80.08

t for H0
Coeff=0
-2.31
0.47
3.81
2.78
6.12
3.34

Prob > |t|


0.0392
0.6501
0.0025
0.0167
< 0.0001
0.0059

The F-value is 12.73 with a corresponding P-value of .0005. Mixing technique has an effect.
(b) Construct a graphical display as described in Section 3-5.3 to compare the mean tensile strengths for
the four mixing techniques. What are your conclusions?

S yi .

MS E

12825.7
56.625
4

2-1

STAT 503, Fall 2005

Homework Solution 2

Due: Sept. 15, 2005

Scaled t Distribution

(4)

(3)

2700

2800

2900

(1)

3000

(2)

3100

Tensile Strength

Based on examination of the plot, we would conclude that 1 and 3 are the same; that 4 differs from

1 and 3 , that 2 differs from 1 and 3 , and that 2 and 4 are different.
(c) Use the Fisher LSD method with =0.05 to make comparisons between pairs of means.

LSD t

,N a

LSD t 0.025 ,16 4

2 MS E
n
2( 12825.7 )
4

LSD 2.179 6412.85 174.495


Treatment 2 vs. Treatment 4 = 3156.250 - 2666.250 = 490.000 > 174.495
Treatment 2 vs. Treatment 3 = 3156.250 - 2933.750 = 222.500 > 174.495
Treatment 2 vs. Treatment 1 = 3156.250 - 2971.000 = 185.250 > 174.495
Treatment 1 vs. Treatment 4 = 2971.000 - 2666.250 = 304.750 > 174.495
Treatment 1 vs. Treatment 3 = 2971.000 - 2933.750 = 37.250 < 174.495
Treatment 3 vs. Treatment 4 = 2933.750 - 2666.250 = 267.500 > 174.495
The Fisher LSD method is also presented in the Design-Expert computer output above. The results agree
with the graphical method for this experiment.
(d) Construct a normal probability plot of the residuals. What conclusion would you draw about the
validity of the normality assumption?
There is nothing unusual about the normal probability plot of residuals.

2-2

STAT 503, Fall 2005

Homework Solution 2

Due: Sept. 15, 2005

Normal plot of residuals


99

Norm al % probability

95
90
80
70
50
30
20
10
5
1

-181.25

-96.4375

-11.625

73.1875

158

Residual

(e) Plot the residuals versus the predicted tensile strength. Comment on the plot.
There is nothing unusual about this plot.
Residuals vs. Predicted
158

Res iduals

73.1875

-11.625

2
-96.4375

-181.25
2666.25

2788.75

2911.25

3033.75

3156.25

Predicted

(f) Prepare a scatter plot of the results to aid the interpretation of the results of this experiment.
Design-Expert automatically generates the scatter plot. The plot below also shows the sample average for
each treatment and the 95 percent confidence interval on the treatment mean.

2-3

STAT 503, Fall 2005

Homework Solution 2

Due: Sept. 15, 2005

One Factor Plot


3300

Tensile Strength

3119.75

2939.51

2759.26

2579.01
1

Technique

(a) Rework part (b) of Problem 3-1 using Tukeys test with = 0.05. Do you get the same
conclusions from Tukeys test that you did from the graphical procedure and/or the Fisher LSD
method?

3.2

Minitab Output
Tukey's pairwise comparisons
Family error rate = 0.0500
Individual error rate = 0.0117
Critical value = 4.20
Intervals for (column level mean) - (row level mean)
1

-423
53

-201
275

-15
460

67
543

252
728

30
505

No, the conclusions are not the same. The mean of Treatment 4 is different than the means of Treatments 1,
2, and 3. However, the mean of Treatment 2 is not different from the means of Treatments 1 and 3
according to the Tukey method, they were found to be different using the graphical method and the Fisher
LSD method.
(b) Explain the difference between the Tukey and Fisher procedures.
Both Tukey and Fisher utilize a single critical value; however, Tukeys is based on the studentized range
statistic while Fishers is based on t distribution.
3-4 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

2-4

STAT 503, Fall 2005

Homework Solution 2

Due: Sept. 15, 2005

materials for the fiber. The engineer conducts an 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

7
12
14
19
7

Observations
15
12
19
22
11

7
17
19
25
10

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.
Minitab Output
One-way ANOVA: Tensile Strength versus Cotton Percentage
Analysis of Variance for Tensile
Source
DF
SS
MS
Cotton P
4
475.76
118.94
Error
20
161.20
8.06
Total
24
636.96

F
14.76

P
0.000

Yes, the F-value is 14.76 with a corresponding P-value of 0.000. The percentage of cotton in the fiber
appears to have an affect on the tensile strength.
(b) Use the Fisher LSD method to make comparisons between the pairs of means. What conclusions can
you draw?
Minitab Output
Fisher's pairwise comparisons
Family error rate = 0.264
Individual error rate = 0.0500
Critical value = 2.086
Intervals for (column level mean) - (row level mean)
15

20

25

20

-9.346
-1.854

25

-11.546
-4.054

-5.946
1.546

30

-15.546
-8.054

-9.946
-2.454

-7.746
-0.254

35

-4.746
2.746

0.854
8.346

3.054
10.546

30

7.054
14.546

In the Minitab output the pairs of treatments that do not contain zero in the pair of numbers indicates that
there is a difference in the pairs of the treatments. 15% cotton is different than 20%, 25% and 30%. 20%
cotton is different than 30% and 35% cotton. 25% cotton is different than 30% and 35% cotton. 30%
cotton is different than 35%.
(c) Analyze the residuals from this experiment and comment on model adequacy.

2-5

STAT 503, Fall 2005

Homework Solution 2

Due: Sept. 15, 2005

The residual plots below show nothing unusual.


Normal Probability Plot of the Residuals
(response is Tensile Strength)
99

95
90

Percent

80
70
60
50
40
30
20
10
5

-5.0

-2.5

0.0
Residual

2.5

5.0

Residuals Versus the Fitted Values


(response is Tensile Strength)
5.0

Residual

2.5

0.0

-2.5

-5.0
10

12

14

16
Fitted Value

18

20

22

3-10 An experiment was run to determine whether four specific firing temperatures affect the density of a
certain type of brick. The experiment led to the following data:
Temperature
100
125
150
175

21.8
21.7
21.9
21.9

Density
21.7
21.5
21.8
21.8

21.9
21.4
21.8
21.7

21.6
21.4
21.6
21.4

(a) Does the firing temperature affect the density of the bricks? Use = 0.05.

2-6

21.7
21.5

STAT 503, Fall 2005

Homework Solution 2

Due: Sept. 15, 2005

No, firing temperature does not affect the density of the bricks. Refer to the Design-Expert output below.
Design Expert Output
Response:
Density
ANOVA for Selected Factorial Model
Analysis of variance table [Partial sum of squares]
Sum of
Mean
Source
Squares
DF
Square
Model
0.16
3
0.052
A
0.16
3
0.052
Residual
0.36
14
0.026
Lack of Fit
0.000
0
Pure Error
0.36
14
0.026
Cor Total
0.52
17

F
Value
2.02
2.02

Prob > F
0.1569
0.1569

not significant

The "Model F-value" of 2.02 implies the model is not significant relative to the noise. There is a
15.69 % chance that a "Model F-value" this large could occur due to noise.
Treatment Means (Adjusted, If Necessary)
Estimated
Standard
Mean
Error
1-100
21.74
0.072

2-125 21.50
3-150 21.72
4-175 21.70
Treatment
1 vs 2
1 vs 3
1 vs 4
2 vs 3
2 vs 4
3 vs 4

Mean
Difference
0.24
0.020
0.040
-0.22
-0.20
0.020

0.080
0.072
0.080
DF
1
1
1
1
1
1

Standard
Error
0.11
0.10
0.11
0.11
0.11
0.11

t for H0
Coeff=0
2.23
0.20
0.37
-2.05
-1.76
0.19

Prob > |t|


0.0425
0.8465
0.7156
0.0601
0.0996
0.8552

(b) Is it appropriate to compare the means using the Fisher LSD method in this experiment?
The analysis of variance tells us that there is no difference in the treatments. There is no need to proceed
with Fishers LSD method to decide which mean is difference.
(c) Analyze the residuals from this experiment. Are the analysis of variance assumptions satisfied? There
is nothing unusual about the residual plots.

2-7

STAT 503, Fall 2005

Homework Solution 2

Due: Sept. 15, 2005

Normal plot of residuals

Residuals vs. Predicted


0.2

99

Norm al % probability

95
90

0.075

Residuals

80
70
50
30
20
10

-0.05
2

-0.175

5
1

-0.3
-0.3

-0.175

-0.05

0.075

0.2

21.50

21.56

Res idual

21.62

21.68

21.74

Predicted

(d)Construct a graphical display of the treatments as described in Section 3-5.3.


Does this graph adequately summarize the results of the analysis of variance in
part (b). Yes.
Scaled t Distribution

(125)

21.2

21.3

21.4

(175,150,100)

21.5

21.6

21.7

21.8

Mean Density

(e)

My procedures for analyzing the data with a regression model are listed below:
1.
2.
3.
4.
5.
6.
7.
8.

Fit the One-way ANOVA model using the original data. The result is not significant;
Fit the Regression model with Temp and Temp**2 as predictors. The result is not significant;
Fit the Regression model with Temp, Temp**2 and Temp**3 as predictors. The result is not
significant;
Minitab output marked obs 18 as an unusual observation. It may be a potential outlier, so, I
removed this point, and redo the above procedures.
Fit the One-way ANOVA model using the new data. The result is significant (p = 0.044);
Fit the Regression model with Temp and Temp**2 as predictors. P-values for Temp and Temp**2
are around 0.05;
Fit the Regression model with Temp, Temp**2 and Temp**3 as predictors. P-values for the three
terms are all around 0.05.
The overall model (after removing the outlier) for the cubic polynomial regression is a better fit
than the quadratic, based on both the p-value for the model and the adjusted R-squared value.

2-8

STAT 503, Fall 2005

Homework Solution 2

Due: Sept. 15, 2005

Minitab output:
MTB > Let c7 = 'Temp' * 'Temp'
MTB > Let c8 = 'Temp' * 'Temp' * 'Temp'
MTB > Oneway 'Density' 'Temp'.

One-way ANOVA: Density versus Temp


Analysis of Variance for Density
Source
DF
SS
MS
Temp
3
0.1561
0.0520
Error
14
0.3600
0.0257
Total
17
0.5161
Level
100
125
150
175

N
5
4
5
4

Mean
21.740
21.500
21.720
21.700

F
2.02

Individual 95% CIs For Mean


Based on Pooled StDev
-------+---------+---------+--------(---------*--------)
(----------*---------)
(--------*---------)
(---------*----------)
-------+---------+---------+--------21.44
21.60
21.76
C7;

StDev
0.114
0.141
0.164
0.216

Pooled StDev =
0.160
MTB > Regress 'Density' 2
SUBC>
Constant;
SUBC>
Brief 2.

P
0.157

'Temp'

Regression Analysis: Density versus Temp, C7


The regression equation is
Density = 23.1 - 0.0221 Temp +0.000082 C7
Predictor
Constant
Temp
C7

Coef
23.100
-0.02209
0.00008178

S = 0.1768

SE Coef
1.212
0.01834
0.00006701

R-Sq = 9.1%

T
19.06
-1.20
1.22

P
0.000
0.247
0.241

R-Sq(adj) = 0.0%

Analysis of Variance
Source
Regression
Residual Error
Total
Source
Temp
C7

DF
1
1

DF
2
15
17

SS
0.04722
0.46889
0.51611

MS
0.02361
0.03126

F
0.76

P
0.487

Seq SS
0.00067
0.04656

Unusual Observations
Obs
Temp
Density
18
175
21.4000

Fit
21.7389

SE Fit
0.0859

Residual
-0.3389

R denotes an observation with a large standardized residual


MTB > Regress 'Density' 3
SUBC>
Constant;
SUBC>
Brief 2.

'Temp' C7 C8;

2-9

St Resid
-2.19R

STAT 503, Fall 2005

Homework Solution 2

Due: Sept. 15, 2005

Regression Analysis: Density versus Temp, C7, C8


The regression equation is
Density = 41.3 - 0.438 Temp + 0.00317 C7 -0.000007 C8
Predictor
Coef
Constant
41.300
Temp
-0.4377
C7
0.003168
C8
-0.00000747
S = 0.1604

SE Coef
8.912
0.2027
0.001501
0.00000363

R-Sq = 30.2%

T
4.63
-2.16
2.11
-2.06

P
0.000
0.049
0.053
0.059

R-Sq(adj) = 15.3%

Analysis of Variance
Source
Regression
Residual Error
Total
Source
Temp
C7
C8

DF
1
1
1

DF
3
14
17

SS
0.15611
0.36000
0.51611

MS
0.05204
0.02571

F
2.02

P
0.157

Seq SS
0.00067
0.04656
0.10889

Unusual Observations
Obs
Temp
Density
18
175
21.4000

Fit
21.7000

SE Fit
0.0802

Residual
-0.3000

St Resid
-2.16R

R denotes an observation with a large standardized residual


MTB > Oneway 'Density' 'Temp'.

One-way ANOVA: Density versus Temp


Analysis of Variance for Density
Source
DF
SS
MS
Temp
3
0.1976
0.0659
Error
13
0.2400
0.0185
Total
16
0.4376
Level
100
125
150
175

N
5
4
5
3

Mean
21.740
21.500
21.720
21.800

Pooled StDev =
0.136
MTB > Regress 'Density' 2
SUBC>
Constant;
SUBC>
Brief 2.

StDev
0.114
0.141
0.164
0.100
'Temp'

F
3.57

P
0.044

Individual 95% CIs For Mean


Based on Pooled StDev
---+---------+---------+---------+--(------*------)
(------*------)
(------*------)
(-------*-------)
---+---------+---------+---------+--21.40
21.60
21.80
22.00
'Temp**2';

Regression Analysis: Density versus Temp, Temp**2


The regression equation is
Density = 23.8 - 0.0332 Temp +0.000127 Temp**2
Predictor

Coef

SE Coef

2-10

STAT 503, Fall 2005


Constant
Temp
Temp**2

Homework Solution 2

23.765
-0.03323
0.00012713

S = 0.1508

1.066
0.01624
0.00005983

R-Sq = 27.2%

22.29
-2.05
2.12

Due: Sept. 15, 2005

0.000
0.060
0.052

R-Sq(adj) = 16.8%

Analysis of Variance
Source
Regression
Residual Error
Total
Source
Temp
Temp**2

DF
2
14
16

DF
1
1

SS
0.11910
0.31855
0.43765

MS
0.05955
0.02275

F
2.62

P
0.108

Seq SS
0.01637
0.10273

MTB > Regress 'Density' 3


SUBC>
Constant;
SUBC>
Brief 2.

'Temp' 'Temp**2' 'Temp**3';

Regression Analysis: Density versus Temp, Temp**2, Temp**3


The regression equation is
Density = 39.3 - 0.388 Temp + 0.00277 Temp**2 -0.000006 Temp**3
Predictor
Coef
Constant
39.300
Temp
-0.3884
Temp**2
0.002768
Temp**3
-0.00000640
S = 0.1359

SE Coef
7.592
0.1728
0.001281
0.00000310

R-Sq = 45.2%

T
5.18
-2.25
2.16
-2.06

P
0.000
0.043
0.050
0.060

R-Sq(adj) = 32.5%

Analysis of Variance
Source
Regression
Residual Error
Total
Source
Temp
Temp**2
Temp**3

DF
1
1
1

DF
3
13
16

SS
0.19765
0.24000
0.43765

MS
0.06588
0.01846

Seq SS
0.01637
0.10273
0.07855

2-11

F
3.57

P
0.044

You might also like