Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
224 views

Tutorial 8 - With Solution

The document describes the results of four experiments that used analysis of variance (ANOVA) to analyze factorial designs. In the first experiment, ANOVA was used to determine if there were differences between four staff training programs based on task performance times. The second used ANOVA to analyze differences between three fertilizers and mango tree yields. The third analyzed the effects of furnace position and firing temperature on carbon anode density. The fourth investigated how material and design affected component lifetime. ANOVA indicated temperature had a significant effect in the third and fourth experiments, while other factors like position, material and their interactions were not always significant.

Uploaded by

Keefwat Tawfeek
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
224 views

Tutorial 8 - With Solution

The document describes the results of four experiments that used analysis of variance (ANOVA) to analyze factorial designs. In the first experiment, ANOVA was used to determine if there were differences between four staff training programs based on task performance times. The second used ANOVA to analyze differences between three fertilizers and mango tree yields. The third analyzed the effects of furnace position and firing temperature on carbon anode density. The fourth investigated how material and design affected component lifetime. ANOVA indicated temperature had a significant effect in the third and fourth experiments, while other factors like position, material and their interactions were not always significant.

Uploaded by

Keefwat Tawfeek
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

Tutorial 8

1.

UTP wishes to compare four programs for training staff to perform a certain task. Twenty new
staffs are randomly selected to the training programs, with 5 in each program. At the end of the
training, a test is conducted to see how quickly trainees can perform the task. The number of
times the task is performed per minute is recorded for each trainee and the results as in table
below:
Program

Time in minutes

Program 1

9, 12, 14, 11, 13

Program 2

12, 14, 11, 13, 11

Program 3

9, 8, 7, 8, 11

Program 4

10, 6, 9, 9, 10

i. Construct the ANOVA table.


ii. Are there any differences between the four programs?
Solution:
i.

ii.

ANOVA
Source of
Variation
Between Groups
Within Groups

SS
54.95
41.6

Total

96.55

df

MS
F
P-value
3 18.31667 7.044872 0.003113
16
2.6
19

Since F > f0.05, 3, 16 = 3.24, so the differences between groups are significance at

2.

A farmer wants to determine which type of fertilizer is best for growing mango trees in his
orchard. He chooses three types of fertilizers, F1, F2 and F3 and treats two mango trees to each
tree is recorded in table below:
Fertilizer

Number of mangoes
from each tree

F1

32, 40

F2

43, 42

F3

20, 10

i. Construct the ANOVA table.


ii. Are there any differences between the three fertilizers?
Solution:
i.
ANOVA
Source of
Variation
Between Groups
Within Groups

SS
826.3333
82.5

Total

908.8333

df

MS
F
2 413.1667 15.02424
3
27.5

P-value
0.02735

ii. Since F > f0.05, 2, 3 = 9.55, so the differences between groups are significance at 05.

3.

An experiment was conducted to determine whether either firing temperature or furnace


position affects the baked density of a carbon anode. The data are as follows:
Temperature (oC)
Low

Position

High

565

1080

583

1043

570

1063

521

1004

547

1026

528

988

i. Construct the 2 X 2 factorial design table.


ii. Find the estimate of all effects and interaction.
iii. Construct the ANOVA table for each effect; test the null hypothesis that the effect is equal
to 0. Interpret your results.
Solution:
i.
Treat:
(I)
p
t
pt

Position, P
+
+

Temp. T
+
+

PxT
+
+

Total
1718
1596
3186
3018

ii.
Effect P =
Effect T =
Effect PXT=

1/6[p + pt - (I) t] = - 48.333


1/6[t + pt (I) p]= 481.667
1/6[(I) + pt p t]=7.667

iii.
SS for position=
SS for temp.=
SS for PxT =
SS for Total =
ANOVA
Source of
Variation
Sample, position
Columns temp.
Interaction
Error
Total

1/12[ p + pt - (I) t ]2 = 7008.33333


1/12[t + pt (I) p]2 = 696008.333
1/12[(I) + pt p t]2 = 176.333333
5652 + 5832 + +9882 - (1718+..+3018)2/12
705141.667

SS
7008.333
696008.3
176.3333
1948.667
705141.7

df
1
1
1
8
11

MS
7008.33
696008.3
176.333
243.583

F
28.77
2857.37
0.724

Since F for position and temperature are very large, so the differences between position and the
differences between temperature are significance at = 0.05.

4.

A two factor experimental design was conducted to investigate the lifetime of a component
being manufactured. The two factors are A (design) and B (cost of material). Two levels ((+) and
(-)) of each factor are considered. Three components are manufactured with each combination
of design and material, and the total lifetime measured (in hours) is as shown in table below

Treatment
Combination
(1)
a
b
ab
i.
ii.
iii.
iv.

Design
A

Material
B

AB

Total lifetime of 3
components
(in hours)

+
+

+
+

+
+

122
60
120
118

Perform a two way analysis of variance to estimate the effects of design and material
expense on the component life time if the sum squares of total are 1050.
Based on your results in part (a), what conclusions can you draw from the factorial
experiment?
Indicate which effects are significant to the lifetime of a component.
Write the least square fitted model using only the significant sources.

Solution:
i.

Given SS for total = 1050


SS for design, D = 1/12[a + ab (1) b]2 = 1/12[60+118-122-120]2 = 341.333
SS for material, M = 1/12[b + ab (1) a]2 = 1/12[120+118-122-60]2 = 261.333
SS for D x M = 1/12[(1) + ab a b]2 = 1/12[122+118-60-120]2 = 300

ANOVA
Source of
Variation
Design, D
Material, M
Interaction, D X M
Error
Total

SS
341.333
261.333
300
147.334
1050

df
1
1
1
8
11

MS
341.33
261.33
300.00
18.42

F
18.53
14.19
16.29

Since F for design, material and their interaction are very large, so the differences between
design, material and their interaction are significance at = 0.05.

5.

An experiment involves a storage battery used in the launching mechanism of a shoulderfired ground-to-air missile. Two material types can be used to make the battery plates. The
objective is to design a battery that is relatively unaffected by the ambient temperature. The
output response from the battery is effective life in hours. Two temperature levels are selected,
and a factorial experiment with four replicates is run. The data are as follows:
Temperature (F)
Material
1

Low

High

130 155 20 70
74 180 82 58

138 110 96 104


168 160 82 60

i. Construct the 2 X 2 factorial design table.


ii. Find the estimate of all effects and interaction.
iii. Construct the ANOVA table for each effect; test the null hypothesis that the effect is equal
to 0. Interpret your results.
iv. Write the least squares fitted model using only the significant terms.
Solution:
i.

Treat:
(I)
m
t
mt

Material,
M
+
+

Temp. T
+
+

PxT
+
+

Total
539
576
230
342

ii.
Effect, material, M =
Effect, temp., T =
Effect, M X T =

1/8[m + mt - (1) - t] = 18.625


1/8[t + mt - (1) - m] = -67.875
1/8[(1) + mt m - t] = 9.375

iii.
SS for material= 1/16[ m + mt - (I) t ]2 = 1387.5625
SS for temp.= 1/16[t + mt (I) p]2 = 18428.0625
SS for MxT = 1/16[(I) + mt m t]2 = 351.5625
1302 + 1552 + +602 - (539+..+342)2/16
SS for Total = 31639.9375

ANOVA
Source of
Variation
Material, M
Temperature, T
Interaction, M x T
Error
Total

SS
1387.5625
18428.0625
351.5625
11472.75
31639.9375

df
1
1
1
12
15

MS
1387.563
18428.06
351.5625
956.0625

F
1.45
19.27
0.37

Since F for temperature is large, so the differences between temperature is significance at =


0.05. The differences between material and the interactions are not significance because F for
material and the interaction < f0.05, 1, 12 = 4.75.

oooOOOooo

Tutorial 8_Sept. 2013/RR

You might also like