Analysis of Variance: A Conceptual Overview Analysis of Variance: A Conceptual Overview

 Assumptions for Analysis of Variance  Sampling Distribution of x Given H0 is True

For each population, the response (dependent)

variable is normally distributed. Sample means are close together
because there is only
The variance of the response variable, denoted  2,
one sampling distribution
is the same for all of the populations. This is also known as when H0 is true.
Assumption of Homogeneity of Variance.
2
The observations must be independent.  x2 
n

x2  x1 x3

36 37

Analysis of Variance: A Conceptual Overview Testing for the Equality of k Population Means:

 Sampling Distribution of x Given H0 is False  Example: Reed Manufacturing

Janet Reed would like to know if there is any
Sample means come from significant difference in the mean number of hours
different sampling distributions worked per week for the department managers at her
and are not as close together three manufacturing plants (in Buffalo, Pittsburgh,
when H0 is false. and Detroit).
An F test will be conducted using a = .05.

x3 3 x1 1 2 x2

38 39

Testing for the Equality of k Population Means: Testing for the Equality of k Population Means:
 Example: Reed Manufacturing
A simple random sample of five managers from Plant 1 Plant 2 Plant 3
each of the three plants was taken and the number of Observation Buffalo Pittsburgh Detroit
hours worked by each manager in the previous week 1 48 73 51
is shown on the next slide. 2 54 63 63
3 57 66 61
4 54 64 54
Identify Factors, Treatments, Experimental units 5 62 56
and Response Variables
74
Sample Mean 55 68 57
Sample Variance 26.0 26.5 24.5

40 41

1
 Testing for the Equality of k Population Means: Testing for the Equality of k Population Means:
 Example: Reed Manufacturing  p -Value and Critical Value Approaches
1. Develop the hypotheses.
Factor . . . Manufacturing plant H0:  1= 2= 3
Treatments . . . Buffalo, Pittsburgh, Detroit Ha: Not all the means are equal
Experimental units . . . Managers where:
Response variable . . . Number of hours worked  1 = mean number of hours worked per
week by the managers at Plant 1
 2 = mean number of hours worked per
week by the managers at Plant 2
  3 = mean number of hours worked per
week by the managers at Plant 3

42 43

Testing for the Equality of k Population Means: Testing for the Equality of k Population Means:

 p -Value and Critical Value Approaches  p -Value and Critical Value Approaches
2. Specify the level of significance. a = .05 3. Compute the value of the test statistic. (con’t.)

Mean Square Due to Error

3. Compute the value of the test statistic.
SSE = 4(26.0) + 4(26.5) + 4(24.5) = 308
Mean Square Due to Treatments MSE = 308/(15 - 3) = 25.667
(Sample sizes are all equal.)
F = MSTR/MSE = 245/25.667 = 9.55
x = (55 + 68 + 57)/3 = 60
SSTR = 5(55 - 60)2 + 5(68 - 60)2 + 5(57 - 60)2 = 490
MSTR = 490/(3 - 1) = 245

44 45

Testing for the Equality of k Population Means: Testing for the Equality of k Population Means:

 ANOVA Table  p –Value Approach

4. Compute the p –value.
Source of Sum of Degrees of Mean
With 2 numerator d.f. and 12 denominator d.f.,
Variation Squares Freedom Square F p-Value
the p-value is .01 for F = 6.93. Therefore, the
Treatment 490 2 245 9.55 .0033 p-value is less than .01 for F = 9.55.
Error 308 12 25.667
5. Determine whether to reject H0.
Total 798 14
The p-value < .05, so we reject H0.
We have sufficient evidence to conclude that the
mean number of hours worked per week by
department managers is not the same at all 3 plant.

46 47

2
 Testing for the Equality of k Population Means: EXAMPLE 3

 Critical Value Approach

4. Determine the critical value and rejection rule.
Based on an F distribution with 2 numerator
d.f. and 12 denominator d.f., F.05 = 3.89.
Reject H0 if F > 3.89
5. Determine whether to reject H0.
Because F = 9.55 > 3.89, we reject H0. •
We have sufficient evidence to conclude that the
mean number of hours worked per week by
department managers is not the same at all 3 plant.
•

48 49

DATA

50