ANOVA 1 F-Ratio

ANALYSIS OF
VARIANCES (ANOVA)
F-Distribution1
Presented by:
MOHAMMAD FAROOQ
ACADEMIC COORDINATOR
MATHEMATICS
LEARNING OBJECTIVES
1. Recall F-Distribution from 4th slide.
2. Analysis of Variance (ANOVA)
One Way Classification
3. The F-test for comparing variances
Utility
 ANOVA is used to test hypotheses about differences
between three or more means.
 The t-test can only be used to test differences between
two means.
 When there are more than two means, it is possible to
compare each mean with each other mean using t-tests.

 However, conducting multiple t-tests can lead to severe
inflation of the Type I error rate.

 ANOVA can be used to test differences among several
means for significance without increasing the Type I error

rate.
Assumptions for the F Test for Comparing
Three or More Means
1. The populations from which the samples

are obtained must be normally or
approximately normally distributed.
2. The samples must be independent of each
other.
3. The variances of the populations must be
equal.
The test of the difference among three
or more means,
H₀ : μ₁ = μ₂ = ∙∙∙ = μn
H₁ : At least one mean is different from others.
The degrees of freedom for k groups

d.f.N. = k - 1, (N = Numerator)
d.f.D. = N - k (D = Denominator)
where N is the sum of the sample sizes
of the groups N = n₁ + n₂ + n .k
Table: Analysis of Variance Table for the Completely
Randomized Design
Source of Sum of square d.f Mean square Variance
variation ratio
Among k k-1 MSA=SSA/(k-1) V.R=MSA/
sample SSA   n (x j .j
 x ..
) 2
MS due to MSW
j 1
Treatment
Within 2 N-k MSW=SSW/(N-k)
k n j
samples SSW    (x x . j) MS due to error
ij 
j 1 i 1
Total N-1
2
k n j
SST    ( x x ..)
ij 
j 1 i 1
The Total Sum of squares(SST): It is the sum of the squares of

the deviations of individual observations taken together.
Example 1 :A researcher whishes to try three different techniques to lower the
blood pressure of individuals diagnosed with the high blood pressure. The
subjects are randomly assigned to three groups; the first group take
medication, the second group exercises, and the third group follows a special
diet. After four weeks the reduction of each person’s is recorded. At α = 0.05,
test the claim that there is no difference among
The means. The data are shown
Medication Exercise Diet
10 6 5
12 8 9
9 3 12
15 0 8
13 2 4
χ₁ = 11.8 χ₂ = 3.8 χ₃ = 7.6
Solution Example 1:
 STEP 1: State the hypothesis and identify the claim.
H₀: μ₁ = μ₂ = μ₃ (claim)
H₁: At least one mean is different from others.
 STEP 2: Find the critical value. Since k =3 and N = 15.

d.f.N. =k – 1 = 3 – 1 = 2
d.f.D. =N – k = 15 – 3 = 12
The critical value is 3.89 obtained from Table H in Appendix C with α =0.05.
 STEP 3: Compute the test value using the procedure outline here.
a. Find the mean and variance of each sample (these values are shown below the
data).
b. Find the grand mean. The grand mean, denoted by is the mean of all values in the
samples.
c. Find the between group variance, denoted by s²B .
d. Find the within-group variance, denoted by

 ,
e. Find the F test value.

SOURCE SUM OF d.f. MEAN F
SQUARES SQUARE
Between 160.13 2 80.07 9.17
Within 104.80 12 8.73
(error)
TOTAL 264.93 14
STEP 4: Make the decision. The decision is to reject the null

hypothesis, since 9.17 > 3.89. ( F0.05,2,12 = 3.89)
95% Confidence Interval for Ratio
of Variances
 
2
s  1  12 s12  
1
    2  df 2 ,df1 , 
F
s  Fdf ,df ,   2 s2 
2 2
2
2
 1 2 2
 1   12
9.17 
F   2  9.17  F12,2,0.025 
 2,12,0.025   2
 1   2
 9.17    1
 9.17  39.41
 5.10   2
2
 12
 1.798  2  361.39
2
The F-Distribution
 Assume we repeatedly select a random
sample of size n from two normal
populations.
 Consider the distribution of the ratio of
two variances: F = s12/s12.

[Note where s1 is the largest or the two variances]
The distribution formed in this manner
approximates an F distribution with the
following degrees of freedom:
v1 = n1 - 1 and v1 = n1 - 1
The F-test for comparing variances
 The F-test is used for comparing two
variances, say  A2 and  B2 .
 The hypothesis being tested is
H 0 :  A2   B2
with either a one-sided alternative
2;
H :  
1 A
2
B
H :  2
1 2
A B
or a two-sided alternative
H1 :  2
A  2
B
Example 2
The variability in the amount of impurities present in a
batch of chemicals used for a particular process
depends on the length of time that the process is in
operation.
Suppose a sample of size 25 is drawn from the normal
process which is to be compared to a sample of a new
process that has been developed to reduce the
variability of impurities at 5% and also find C I for 90%
Sample 1 Sample 2
N 25 25
s2 1.04 0.51
Solution Example 2
H0: s12 = s22
Ha: s12 > s22
F = s12/s22 = 1.04/.51 = 2.04
F24,24,0.05  1.98
a = 0.05 cv = 1.98 < 2.04
Thus, reject H0 and conclude that the variability in the
new process (Sample 2) is less than the variability in
the original process.
90% Confidence Interval
 1  1
2
2.04    2  2.04  1.98 
 1.98   2
 12
 1.030  2  4.039
2
Confidence Interval for Ratio of Variances
Example 3
Background Samples Study Site Samples
n2  6 n1  8
y2  2.48 y1  4.82
s2  1.13 s1  0.89
5,7,0.025 5
F .29
Example (95% CI): 7,5,0.025 6
F .98
 1 
2 2 2
1
.13 1
.13
 2 2 6
 
1
2
.9
8
0
.895 9 
.2 2 0
.89
2
0
.34 1
0 1
1.2
52
2
2
Example 4 class work
Among 11 patients in a certain study, the
standard deviation of the property of interest was
5.8. In another group of 4 patients, the standard
deviation was 3.4. We wish to construct a 95
percent confidence interval for the ratio of the
variances of these two populations and
determine whether the variability of the property
of interest among 11 patients is lesser than 4
patients.
Solution continued
Calculation of the 95% confidence interval for /

17

ANOVA 1 F-Ratio

Uploaded by

Copyright:

Available Formats

ANOVA 1 F-Ratio

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

ANOVA 1 F-Ratio

Uploaded by

Copyright:

Available Formats

ANALYSIS OF

compare each mean with each other mean using t-tests.

inflation of the Type I error rate.

means for significance without increasing the Type I error

1. The populations from which the samples

The degrees of freedom for k groups

The Total Sum of squares(SST): It is the sum of the squares of

 STEP 2: Find the critical value. Since k =3 and N = 15.

d. Find the within-group variance, denoted by

e. Find the F test value.

STEP 4: Make the decision. The decision is to reject the null

two variances: F = s12/s12.

You might also like