This action might not be possible to undo. Are you sure you want to continue?
2
The oneway analysis of variance is used to test
the claim that three or more population means
are equal
This is an extension of the two independent
samples ttest samples ttest
Oneway ANOVA – An analysis of variance
procedure using one dependent and one
independent variable.
3
The response variable is the variable you’re
comparing
The factor variable is the categorical variable
being used to define the groups
◦ We will assume k samples (groups)
The oneway is because each value is classified in
exactly one way
◦ Examples include comparisons by gender, race, political
party, color, etc.
4
To use the oneway ANOVA test, the following
assumptions must be true
◦ The population under study have normal
distribution
◦ The samples are drawn randomly, and each
sample is independent of the other samples.
◦ All the populations from which the samples
values are obtained, have the same unknown
population variance, that is for k number of
populations,
2 2 2
1 2 k
σ σ σ = = = K
5
There is a “family” of F
Distributions.
Each member of the family is
determined by two parameters:
◦ the numerator degrees of freedom
◦ the denominator degrees of freedom.
F cannot be negative, and it is a
continuous distribution.
The F distribution is positively
skewed.
Its values range from 0 to ∞
As F → ∞ the curve approaches
the Xaxis.
6
Only one classification factor is
considered
Factor
1
Response/ outcome/
Treatment
1
2
i
(The level of
the factor)
Response/ outcome/
dependent variable
(samples)
Replicates (1,…,j)
The object to a
given treatment
7
H HH H
0 00 0
: : : : µ µµ µ
1 11 1
= = = = µ µµ µ
2 22 2
= = = = µ µµ µ
3 33 3
= ... = = ... = = ... = = ... = µ µµ µ
k kk k
— All population means All population means All population means All population means
are equal are equal are equal are equal
— No treatment effect No treatment effect No treatment effect No treatment effect
H HH H
a aa a
: Not All : Not All : Not All : Not All µ µµ µ
i ii i
Are Equal Are Equal Are Equal Are Equal
— At least 2 pop. means At least 2 pop. means At least 2 pop. means At least 2 pop. means
X
f(X)
µ µµ µ
1
= µ µµ µ
2
= µ µµ µ
3
Mean square
(variance)
within
— At least 2 pop. means At least 2 pop. means At least 2 pop. means At least 2 pop. means
are different are different are different are different
— Treatment effect Treatment effect Treatment effect Treatment effect
— µ µµ µ
1 11 1
≠ ≠≠ ≠ µ µµ µ
2 22 2
≠ ≠≠ ≠ ... ... ... ... ≠ ≠≠ ≠ µ µµ µ
k k k k
is is is is
Wrong Wrong Wrong Wrong
µ µµ µ
1
µ µµ µ
2
µ µµ µ
3
1 2 3
X
f(X)
µ µµ µ = µ µµ µ µ µµ µ
Mean square among
8
If the null hypothesis is true,
◦ we would expect all the sample means to be close
to one another (and as a result, close to the grand
mean). mean).
If the alternative hypothesis is true,
◦ at least some of the sample means would differ.
9
Variation
◦ Variation is the sum of the squares of the
deviations between a value and the mean of
the value.
As long as the values are not identical, As long as the values are not identical,
there will be variation
Denoted as SS for Sum of Squares
10
Are all of the values identical?
◦ No, so there is some variation in the data
◦ This is called the total variation
◦ Denoted SS(Total) for the total Sum of ◦ Denoted SS(Total) for the total Sum of
Squares (variation)
◦ Sum of Squares is another name for variation
11
VARIATION BETWEEN GROUPS
◦ Are all of the sample means identical?
No, so there is some variation between the groups
for each data value look at the difference between its
group mean and the overall mean. This is called the group mean and the overall mean. This is called the
between group variation
Sometimes called the variation due to the factor
Denoted SS(A) for Sum of Squares (variation)
between the groups
( )
2
x x
i
−
12
VARIATION WITHIN GROUPS
◦ Are each of the values within each group identical?
No, there is some variation within the groups.
for each data value we look at the difference between that
value and the mean of its group.This is called the within value and the mean of its group.This is called the within
group variation
Sometimes called the error variation
Denoted SS(E) for Sum of Squares (variation) within
the groups
• for each data value we look at the difference
between that value and the mean of its group
( )
2
i ij
x x −
13
Variance is described as Sum of Squares
Total Variance is partitioned as follows:
SS
TOTAL
SS
TOTAL
SS
BETWEEN
SS
WITHIN
14
ONEWAY ANOVA TABLE
Source SS df MS F
Between Between
(Factor)
Within
(Error)
Total
15
Oneway Analysis of Variance
Source DF SS MS F
Factor 2 2510.5 1255.3 93.44 0.000
Error 12 161.2 13.4
“F” means “F test statistic”
Error 12 161.2 13.4
Total 14 2671.7
“Source” means “find the components of variation in this column”
“DF” means “degrees of freedom”
“SS” means “sums of squares”
“MS” means “mean squared”
16
Oneway Analysis of Variance
Source DF SS MS F
Factor 2 2510.5 1255.3 93.44 0.000
Error 12 161.2 13.4 Error 12 161.2 13.4
Total 14 2671.7
“Factor” means “Variability between groups” or “Variability due to
the factor of interest”
“Error” means “Variability within groups” or “unexplained random
variation”
“Total” means “Total variation from the grand mean”
17
Oneway Analysis of Variance
Source DF SS MS F
Factor a1 SS(Between) MSA MSA/MSE
Error na SS(Error) MSE Error na SS(Error) MSE
Total n1 SS(Total)
MSA = SS(Between)/(a1)
MSE = SS(Error)/(na)
n1 = (a1) + (na)
SS(Total) = SS(Between) + SS(Error)
18
( )
) x x ( SSE
n
x
x ) x x ( SST
obs
2
i ij
2
ij
2
ij
2
obs
ij
− =
− = − =
∑
∑∑
∑
∑
( )
MSE
MSA
F ;
DF
SS
MS ; SSE SSA SST
n
x
n
) x (
) x x ( SSA
2
ij
i
2
i 2
obs
i
obs
= = + =
− = − =
∑
∑
∑
∑
∑
19
α αα α
If means are equal,
F = MST / MSE ≈ ≈≈ ≈ 1.
Only reject if large F!
Reject H
0
α αα α
Always OneTail!
F
(α; k – 1, n – k)
0
Do Not
Reject H
0
F
© 19841994 T/Maker Co.
If MST is close to MSE then both have same source of variation
20
As production manager, you want to see if three filling
machines have different mean filling times. You assign
15 similarly trained and experienced workers, 5 per
machine, to the machines. At the 5% level of
significance, is there a difference in mean filling times?
Mach1 Mach1 Mach2 Mach2 Mach3 Mach3
25.40 25.40 23.40 23.40 20.00 20.00
26.31 26.31 21.80 21.80 22.20 22.20
24.10 24.10 23.50 23.50 19.75 19.75
23.74 23.74 22.75 22.75 20.60 20.60
25.10 25.10 21.60 21.60 20.40 20.40
21
The summary statistics for the three filling
machines of each row are shown in the table
below
Row Mach 1 Mach 2 Mach 3 Row Mach 1 Mach 2 Mach 3
Sample
size
5 5 5
Total
124.65 113.05 102.95
22
The H
0
is that the means are all equal
◦ H
0
: All machines have equal mean filling times
The alternative hypothesis is that at least one of the The alternative hypothesis is that at least one of the
means is different:
◦ H
1
: Not All machines have equal mean filling times
23
( )
∑
∑ ∑
∑
− = − =
n
x
n
) x (
) x x ( SSA
2
ij
i
2
i
2
obs
i
( )
65 . 340 95 . 102 05 . 113 65 . 124
2
2 2 2
( )
∑
−
+ + =
15
65 . 340
5
95 . 102
5
05 . 113
5
65 . 124
2
2 2 2
162 . 7736 326 . 7783 − =
164 . 47 =
24
( )
∑∑
∑
∑
− = − =
n
x
x ) x x ( SST
2
ij
2
ij
2
obs
ij
[ ] 162 . 7736 4 . 20 ... 1 . 24 31 . 26 4 . 25
2 2 2 2
− + + + + =
2172 . 58 =
162 . 7736 379 . 7794 − =
[ ] 162 . 7736 4 . 20 ... 1 . 24 31 . 26 4 . 25
2 2 2 2
− + + + + =
25
SSA SST SSE
SSE SSA SST
− =
+ =
SSA SST SSE − =
164 . 47 2172 . 58 − =
0532 . 11 =
26
Source Source SS SS df df MS MS F F
Between Between
(Machines) (Machines)
47.1640
Within (Error) Within (Error)
11.0532
Total Total
58.2172
27
Source SS df MS F
Between
(Machines)
47.1640 3  1 = 2
Filling in the degrees of freedom gives this …
(Machines)
47.1640 3  1 = 2
Within (Error)
11.0532 15  3 = 12
Total
58.2172 15  1 = 14
28
Source Source SS SS df df MS MS F F
Between Between
(Machines) (Machines)
47.1640 3  1 = 2 23.5820
Completing the MS gives …
(Machines) (Machines)
47.1640 3  1 = 2 23.5820
Within (Error) Within (Error)
11.0532 15  3 = 12 0.9211
Total Total
58.2172 15  1 = 14
29
Source SS df MS F
Between
(Machines)
47.1640 3  1 = 2 23.5820
25.60
Adding F to the table …
(Machines)
47.1640 3  1 = 2 23.5820
25.60
Within (Error)
11.0532 15  3 = 12 0.9211
Total
58.2172 15  1 = 14
30
H HH H
0 00 0
: : : : µ µµ µ
1 11 1
= = = = µ µµ µ
2 22 2
= = = = µ µµ µ
3 33 3
H HH H
1 11 1
: : : : Not all mean equal Not all mean equal Not all mean equal Not all mean equal
Critical Value(s): Critical Value(s): Critical Value(s): Critical Value(s):
α αα α = = = = .05
Test Statistic:
F
MST
MSE
= == = = == = = == =
23 5820
9211
25.6
.
.
F
0 3.89
α αα α = = = = .05
ν νν ν
1 11 1
= = = = 2 ν νν ν
2 22 2
= = = = 12
Decision:
Conclusion:
Reject at α αα α = .05
There is evidence that three
filling machines have different
mean filling times
α αα α = .05
.
31
Oneway ANOVA: time versus Machine
Source DF SS MS F P
Machine 2 47.164 23.582 25.60 0.000
Error 12 11.053 0.921
Total 14 58.217
S = 0.9597 RSq = 81.01% RSq(adj) = 77.85%
Individual 95% CIs For Mean Based on
Pooled StDev
Level N Mean StDev ++++
1 5 24.930 1.032 (*)
2 5 22.610 0.882 (*)
3 5 20.590 0.959 (*)
++++
20.8 22.4 24.0 25.6
Pooled StDev = 0.960
32
33
An experiment was performed to determine whether
the annealing temperature of ductile iron affects its
tensile strength. Five specimens were annealed at each
of four temperatures. The tensile strength (in ksi) was
measured for each temperature. The results are
presented in the following table. Can you conclude that
there are differences among the mean strengths?
presented in the following table. Can you conclude that
there are differences among the mean strengths?
Temperature
(
o
C)
Sample Values
750 19.72 20.88 19.63 18.68 17.89
800 16.01 20.04 18.10 20.28 20.53
850 16.66 17.38 14.49 18.21 15.58
900 16.93 14.49 16.15 15.53 13.25
34
Temperature
(
o
C)
Sample Sample Sample Sample
size (n) size (n) size (n) size (n)
Total Total Total Total
750
800
850
900
35
36
Oneway ANOVA: strength versus Temperature
Source DF SS MS F P
Temperature 3 58.65 19.55 8.49 0.001
Error 16 36.84 2.30
Total 19 95.49
S = 1.517 RSq = 61.42% RSq(adj) = 54.19%
Individual 95% CIs For Mean Based on
Pooled StDev
Level N Mean StDev ++++
750 5 19.360 1.133 (*)
800 5 18.992 1.924 (*)
850 5 16.464 1.467 (*)
900 5 15.270 1.439 (*)
++++
14.0 16.0 18.0 20.0
Pooled StDev = 1.517
37
38
MSE
Confidence interval for each mean, µ
i
i
a n
n
MSE
t x
−
±
,
2
α
39
( )
X X t MSE
n n
1 2
1 2
1 1
− ± +

\

¹

where t is obtained from the t table with degrees of
freedom (n  k).
MSE = [SSE/(n  k)]
n n
1 2
\ ¹
40
When the null hypothesis is rejected, it may
be desirable to find which mean(s) is (are)
different.
Two statistical inference procedures, geared Two statistical inference procedures, geared
at doing this, are presented:
◦ “regular” confidence interval calculations
◦ Tukey test
41
Two means are considered different if the
confidence interval for the difference
between the corresponding sample
means does not contain 0.
In this case the larger sample mean is In this case the larger sample mean is
believed to be associated with a larger
population mean.
42
Tukey 95% Simultaneous Confidence Intervals
All Pairwise Comparisons among Levels of Machine
Individual confidence level = 97.94%
Machine = 1 subtracted from:
Machine Lower Center Upper ++++
2 3.9381 2.3200 0.7019 (*) 2 3.9381 2.3200 0.7019 (*)
3 5.9581 4.3400 2.7219 (*)
++++
5.0 2.5 0.0 2.5
Machine = 2 subtracted from:
Machine Lower Center Upper ++++
3 3.6381 2.0200 0.4019 (*)
++++
5.0 2.5 0.0 2.5
43
44
Only two classification factor is considered Only two classification factor is considered Only two classification factor is considered Only two classification factor is considered
Factor B
1 2 j 1 2 j
Factor A
1
2
i
45
The standard twoway ANOVA tests are valid under the
following conditions:
◦ The design must be complete
Observations are taken on every possible treatment
◦ The design must be balanced
The number of replicates is the same for each treatment The number of replicates is the same for each treatment
◦ The number of replicates per treatment, k must be at least 2
◦ Within any treatment, the observations are a simple random
sample from a normal population
◦ The sample observations are independent of each other (the
samples are not matched or paired in any way)
◦ The population variance is the same for all treatments.
46
2
2 ...
. .
1
1
b
j
j
x
SSB x
an abn
=
= −
∑
1
SSA
MSA
a
=
−
test
MSA
F
MSE
=
2
2
...
..
1
1
a
i
i
x
SSA x
bn abn
=
= −
∑
1
SSB
MSB
b
=
−
test
MSB
F
MSE
=
Source
(Df)
Sum of Squares (SS) Mean of Squares (MS) F Value
A a  1
B b  1
Row
effect
Column
effect
2
2 ...
.
1 1
1
a b
ij
i j
x
SSAB x
n abn
= =
= −
∑∑
2
Error
SSE
MSE
N k
σ = =
−
)
2
2 ...
1 1 1
a b n
ijk
i j k
x
SST x
abn
= = =
= −
∑∑∑
( )( )
1 1
SSAB
MSAB
a b
=
− −
( )
1
SSE
MSE
ab n
=
−
SSE SST SSA
SSB SSAB
= −
− −
1 b −
test
MSE
test
MSAB
F
MSE
=
Interaction
(a1)(b1)
Error ab(n1)
Total abn1
effect
Interaction
effect
47
A chemical engineer is studying the effects of various reagents
and catalyst on the yield of a certain process. Yield is expressed
as a percentage of a theoretical maximum. 4 runs of the process
were made for each combination of 3 reagents and 4 catalysts.
Construct an ANOVA table and test is there an interaction
effect between reagents and catalyst.
Reagent
Catalyst
Reagent
1 2 3
A 86.8 82.4
86.7 83.5
93.4 85.2
94.8 83.1
77.9 89.6
89.9 83.7
B 71.9 72.1
80.0 77.4
74.5 87.1
71.9 84.1
87.5 82.7
78.3 90.1
C 65.5 72.4
76.6 66.7
66.7 77.1
76.7 86.1
72.7 77.8
83.5 78.8
D 63.9 70.4
77.2 81.2
73.7 81.6
84.2 84.9
79.8 75.7
80.5 72.9
48
2
The oneway analysis of variance is used to test the claim that three or more population means are equal This is an extension of the two independent samples ttest Oneway ANOVA – An analysis of variance procedure using one dependent and one independent variable.
3
The response variable is the variable you’re comparing The factor variable is the categorical variable being used to define the groups
◦ We will assume k samples (groups)
The oneway is because each value is classified in exactly one way
◦ Examples include comparisons by gender, race, political party, color, etc.
4
◦ All the populations from which the samples values are obtained. have the same unknown population variance. and each sample is independent of the other samples.To use the oneway ANOVA test. σ 2 1 = σ 2 2 = K = σ 2 k 5 . that is for k number of populations. the following assumptions must be true ◦ The population under study have normal distribution ◦ The samples are drawn randomly.
The F distribution is positively skewed. 6 .There is a “family” of F Distributions. F cannot be negative. and it is a continuous distribution. Its values range from 0 to ∞ As F → ∞ the curve approaches the Xaxis. Each member of the family is determined by two parameters: ◦ the numerator degrees of freedom ◦ the denominator degrees of freedom.
j) The object to a given treatment 7 .….Only one classification factor is considered Factor 1 Treatment 2 (The level of the factor) Response/ outcome/ dependent variable (samples) i Replicates (1.
H0: µ1 = µ2 = µ3 = .. ≠ µk is Wrong f(X) Mean square (variance) within µ1 = µ2 = µ3 f(X) X Mean square among µ1 = µ 2 µ 3 X 8 .. = µk — All population means are equal — No treatment effect Ha: Not All µi Are Equal — At least 2 pop. means are different — Treatment effect — µ1 ≠ µ2 ≠ ...
◦ we would expect all the sample means to be close to one another (and as a result.If the null hypothesis is true. If the alternative hypothesis is true. 9 . ◦ at least some of the sample means would differ. close to the grand mean).
there will be variation Denoted as SS for Sum of Squares 10 . As long as the values are not identical.Variation ◦ Variation is the sum of the squares of the deviations between a value and the mean of the value.
so there is some variation in the data ◦ This is called the total variation ◦ Denoted SS(Total) for the total Sum of Squares (variation) ◦ Sum of Squares is another name for variation 11 .Are all of the values identical? ◦ No.
This is called the between group variation Sometimes called the variation due to the factor Denoted SS(A) for Sum of Squares (variation) between the groups (xi − x ) 2 12 .VARIATION BETWEEN GROUPS ◦ Are all of the sample means identical? No. so there is some variation between the groups for each data value look at the difference between its group mean and the overall mean.
VARIATION WITHIN GROUPS ◦ Are each of the values within each group identical? No.This is called the within group variation Sometimes called the error variation Denoted SS(E) for Sum of Squares (variation) within the groups • for each data value we x 2 at the difference x ij − look i between that value and the mean of its group ( ) 13 . for each data value we look at the difference between that value and the mean of its group. there is some variation within the groups.
Variance is described as Sum of Squares Total Variance is partitioned as follows: SS TOTAL SSBETWEEN SS WITHIN 14 .
ONEWAY ANOVA TABLE Source Between (Factor) Within (Error) Total 15 SS df MS F .
7 “F” means “F test statistic” MS 1255.44 0.000 “Source” means “find the components of variation in this column” “DF” means “degrees of freedom” “SS” means “sums of squares” “MS” means “mean squared” 16 .3 13.2 2671.5 161.Oneway Analysis of Variance Source Factor Error Total DF 2 12 14 SS 2510.4 F 93.
3 13.7 MS 1255.000 “Factor” means “Variability between groups” or “Variability due to the factor of interest” “Error” means “Variability within groups” or “unexplained random variation” “Total” means “Total variation from the grand mean” 17 .4 F 93.44 0.Oneway Analysis of Variance Source Factor Error Total DF 2 12 14 SS 2510.5 161.2 2671.
Oneway Analysis of Variance Source Factor Error Total DF a1 na n1 SS MS SS(Between) MSA SS(Error) MSE SS(Total) F MSA/MSE n1 = (a1) + (na) MSA = SS(Between)/(a1) MSE = SS(Error)/(na) 18 SS(Total) = SS(Between) + SS(Error) .
MS = .SST = ∑ (x ij − x) = ∑∑ 2 obs 2 x ij (∑ x ) − ij 2 n SSE = ∑ (x ij − x i ) 2 obs (∑ x i ) SSA = ∑ (x i − x ) = ∑ − ni obs 2 2 (∑ x ) ij 2 n SS MSA SST = SSA + SSE. F= DF MSE 19 .
If means are equal. Only reject if large F! Reject H0 Do Not Reject H0 0 α F F(α. If MST is close to MSE then both have same source of variation 20 . n – k) Always OneTail! © 19841994 T/Maker Co. F = MST / MSE ≈ 1. k – 1.
40 20. At the 5% level of significance.00 21.75 22.31 24.10 23.60 21.40 26.75 20.60 20.74 25.20 23. is there a difference in mean filling times? Mach1 25.As production manager.80 22. you want to see if three filling machines have different mean filling times.10 Mach2 Mach3 23. 5 per machine.50 19. You assign 15 similarly trained and experienced workers.40 21 . to the machines.
95 22 .The summary statistics for the three filling machines of each row are shown in the table below Row Sample size Total Mach 1 5 124.65 Mach 2 5 113.05 Mach 3 5 102.
The H0 is that the means are all equal ◦ H0: All machines have equal mean filling times The alternative hypothesis is that at least one of the means is different: ◦ H1 : Not All machines have equal mean filling times 23 .
162 = 47.164 24 .SSA = ∑ ( x i − x ) = ∑ 2 obs (∑ x i ) ni 2 (∑ x ) − ij 2 n 124.65)2 = ∑ + + − 5 5 15 5 = 7783.652 113.952 (340.052 102.326 − 7736.
. 2 2 2 2 [ ] = 7794.4 − 7736162 .2172 25 .1 +.4 + 26.SST = ∑ ( x ij − x ) = ∑∑ x 2 obs 2 ij (∑ x ) − ij 2 n = 25.31 + 24.162 = 58..379 − 7736.+ 20.
0532 26 .SST = SSA + SSE SSE = SST − SSA = 58.164 = 11.2172 − 47.
2172 df MS F 27 .0532 58.Source Between (Machines) Within (Error) Total SS 47.1640 11.
0532 15 .1 = 14 28 .1640 df 31=2 MS F 11.2172 15 .Filling in the degrees of freedom gives this … Source Between (Machines) Within (Error) Total SS 47.3 = 12 58.
1640 11.1 = 14 29 .0532 df 31=2 15 .Completing the MS gives … Source Between (Machines) Within (Error) SS 47.9211 F Total 58.2172 15 .3 = 12 MS 23.5820 0.
Adding F to the table … Source Between (Machines) SS 47.3 = 12 0.0532 15 .2172 15 .9211 Total 58.5820 F 25.1 = 14 30 .1640 df 31=2 MS 23.60 Within (Error) 11.
05 ν1 = 2 ν2 = 12 α = .9211 = 25.5820 .05 Conclusion: 0 3.6 Decision: Reject at α = .05 F= MST MSE = 23 .89 31 F There is evidence that three filling machines have different mean filling times .H0: µ1 = µ2 = µ3 H1: Not all mean equal Critical Value(s): Test Statistic: α = .
053 58.01% RSq(adj) = 77.921 F 25.590 StDev 1.960 32 .9597 RSq = 81.164 11.6 Pooled StDev = 0.000 S = 0.582 0.217 MS 23.930 22.032 0.8 22.Oneway ANOVA: time versus Machine Source Machine Error Total DF 2 12 14 SS 47.882 0.0 25.60 P 0.85% Level 1 2 3 N 5 5 5 Mean 24.4 24.959 Individual 95% CIs For Mean Based on Pooled StDev ++++(*) (*) (*) ++++20.610 20.
33 .
04 17.63 18.53 15.10 14. The tensile strength (in ksi) was measured for each temperature.53 17. Five specimens were annealed at each of four temperatures.66 16.89 20.49 16.25 .93 20.28 18.58 13.21 15.An experiment was performed to determine whether the annealing temperature of ductile iron affects its tensile strength.68 20.38 14.01 16.88 20. Can you conclude that there are differences among the mean strengths? Temperature (oC) 750 800 850 900 34 Sample Values 19.72 16.49 19.15 18. The results are presented in the following table.
Temperature (oC) 750 800 850 900 Sample size (n) Total 35 .
36 .
992 16.133 1.0 18.924 1.360 18.439 Individual 95% CIs For Mean Based on Pooled StDev ++++(*) (*) (*) (*) ++++14.49 MS 19.0 20.19% Level 750 800 850 900 N 5 5 5 5 Mean 19.42% RSq(adj) = 54.464 15.517 DF 3 16 19 SS 58.467 1.001 RSq = 61.30 F 8.65 36.84 95.0 16.49 P 0.517 37 .270 StDev 1.0 Pooled StDev = 1.55 2.Oneway ANOVA: strength versus Temperature Source Temperature Error Total S = 1.
38 .
µi x ± tα 2 .Confidence interval for each mean.n − a MSE ni 39 .
k). MSE = [SSE/(n .k)] 40 .1 1 ( X 1 − X 2 ) ± t MSE n + n 1 2 where t is obtained from the t table with degrees of freedom (n .
geared at doing this. it may be desirable to find which mean(s) is (are) different. Two statistical inference procedures.When the null hypothesis is rejected. are presented: ◦ “regular” confidence interval calculations ◦ Tukey test 41 .
In this case the larger sample mean is believed to be associated with a larger population mean.Two means are considered different if the confidence interval for the difference between the corresponding sample means does not contain 0. 42 .
3400 Upper 0.5 Machine = 2 subtracted from: Machine 3 Lower 3.94% Machine = 1 subtracted from: Machine 2 3 Lower 3.0 2.0200 Upper 0.0 2.9381 5.0 2.4019 ++++(*) ++++5.7019 2.9581 Center 2.7219 ++++(*) (*) ++++5.0 2.5 0.5 0.3200 4.5 43 .Tukey 95% Simultaneous Confidence Intervals All Pairwise Comparisons among Levels of Machine Individual confidence level = 97.6381 Center 2.
44 .
Only two classification factor is considered Factor B 1 1 Factor A 2 i 2 j 45 .
k must be at least 2 ◦ Within any treatment. the observations are a simple random sample from a normal population ◦ The sample observations are independent of each other (the samples are not matched or paired in any way) ◦ The population variance is the same for all treatments.The standard twoway ANOVA tests are valid under the following conditions: ◦ The design must be complete Observations are taken on every possible treatment ◦ The design must be balanced The number of replicates is the same for each treatment ◦ The number of replicates per treatment. 46 .
. SSA = ∑ xi. SST = ∑∑∑ x − abn i =1 j =1 k =1 a b n 2 ijk 47 .. 1 a b 2 SSAB = ∑∑ xij ...1 SSB = x2 1 b 2 x.... j..Source A (Df) Sum of Squares (SS) 2 1 a 2 x. − .. ∑ abn an j =1 Ftest = Ftest = MSB MSE MSAB MSE Interaction (a1)(b1) 2 x. − n i =1 j =1 abn MSAB = SSAB ( a − 1)( b − 1) Error ab(n1) SSE = SST − SSA SSE ) σ = MSE = − SSB N −SSAB − k 2 Error MSE = SSE ab ( n − 1) Total abn1 2 x. − bn i =1 abn Mean of Squares (MS) F Value a1 MSA = MSB = SSA a −1 SSB b −1 Ftest = MSA MSE Row effect Column effect Interaction effect B b.
4 85.1 71.9 83.8 83. Construct an ANOVA table and test is there an interaction effect between reagents and catalyst. Yield is expressed as a percentage of a theoretical maximum.5 72. 4 runs of the process were made for each combination of 3 reagents and 4 catalysts.5 82.1 66.2 2 93.6 66.7 83.1 80.5 72.7 77.A chemical engineer is studying the effects of various reagents and catalyst on the yield of a certain process.9 72.0 77.7 78.6 84.2 84.6 89.2 81. Reagent Catalyst A B C D 48 1 86.9 .1 76.9 89.7 80.8 75.4 86.3 90.7 77.7 63.9 3 77.1 72.4 76.8 79.1 73.9 70.7 87.4 65.7 86.4 77.9 84.2 94.7 81.1 74.5 71.8 82.8 83.5 87.5 78.