1. The Analysis of Variance ANOVA
Hypothesis Testing
The Analysis of Variance
ANOVA

2. Introduction
ANOVA handles situations with more than two samples or categories to compare
Easiest to think of ANOVA as an extension of the t test for the significance of the difference between two sample’s means (Chap. 9)
But the t test was limited to the two-sample case
Example from your book
We want to find if the attitude toward capital punishment is related significantly to age
We will want to know which age group shows the most support for capital punishment

3. Example in your book
Table 10.1 shows little difference among the age groups
The means are about the same
And the standard deviation is the same for both tables
What does this tell you?
They all show about the same support for capital punishment
And, there is around the same amount of diversity on support for capital punishment for each group
This would support the null hypothesis

4. Table 10.2
Higher numbers are more likely to oppose the death penalty. The oldest group shows the least support for capital punishment, and the youngest group shows the most support
Again, the greater the differences between categories relative to the differences within categories, the more likely the null is false, and there really is a difference among the groups
If groups are really different, then the sample mean for each should be quite different from the others and dispersion within the categories should be relatively low

5. The Logic of the Analysis of Variance
The null hypothesis for ANOVA
Is that the populations from which the samples are drawn are equal on the characteristic of interest
In other words, the null hypothesis for ANOVA is that the population means are equal
For the example, the null is stated that people of various age groups do not vary in their support for the death penalty
If the null is true, then the average score for the youngest group should be about the same as the average score for the all the other groups

6. Logic, continued
The averages are unlikely to be exactly the same value, even if the null really is true, since there is always some error or chance fluctuations in the measurement process
Therefore, we are not asking if there are differences among the age groups in the sample, but are asking if the differences among the age groups are large enough to justify a decision to reject the null hypothesis and say there are differences in the populations
The researcher will be interested in rejecting the null—to show that support for capital punishment is related to age

7. Logic, continued Basically, what ANOVA does
It compares the amount of variation between categories with the amount of variation within categories
The greater the differences between categories, relative to the differences within categories, the more likely that the null of “no difference” is false and can be rejected

8. The Computation of ANOVA
We will be looking at the variances within samples and between samples
The variance of the distribution is the standard deviation squared, and both are measures of dispersion or variability (or measures of heterogeneity)

9. Computation, continued
We will have two separate estimates of the population variance
One will be the pattern of variation within the categories which is called the sum of squares within (SSW)
The other is based on the variation between categories and is called the sum of squares between (SSB)
The relationship of these three sums of squares is Formula 10.2
SST = SSB + SSW

10. Five-Step Model for ANOVA

11. Step 1
In the ANOVA test, the assumption that must be made with regard to the population variances is that they are equal
If not equal, then ANOVA cannot separate effects of different means from effects of different variances
If the sample sizes are nearly equal, some of the assumptions can be relaxed, but if they are very different, it would be better to use the Chi Square test (in next chapter) but you will have to collapse the data into a few categories

12. Step 2
The null hypothesis states that the means of the populations from which the samples were drawn are equal
The alternative (research) hypothesis states simply that at least one of the population means is different
If we reject the null, ANOVA does not identify which of the means are significantly different
In the ANOVA test, if the null hypothesis is true, then SSB and SSW should be roughly equal in value

13. Step 3
Selecting the sampling distribution and establishing the critical region
The sampling distribution for ANOVA is the F distribution, which is summarized in Appendix D
There are separate tables for alphas of .05 and .01, respectively
The value of the critical F score will vary by degrees of freedom

14. Step 3, continued
For ANOVA, there are two separate degrees of freedom, one for each estimate of the population variance
The numbers across the top of the table are the degrees of freedom associated with the between estimate (dfb), and the numbers down the side of the table are those associated with the within estimate (dfw)
In the two F tables, all the values are greater than 1.00
This is because ANOVA is a one-tailed test and we are concerned only with outcomes in which there is more variance between categories than within categories
F values of less than 1.00 would indicate that the between estimate was lower in value than the within estimate and, since we would always fail to reject the null in such cases, we simply ignore this class of outcomes

15. Step 4
Computing the test statistic.
This is the F ratio

16. Step 5
Making a decision
If our F (obtained) exceeds the F (critical), we reject the null
So, in the test of ANOVA, if the test statistic falls in the critical region, we may conclude that at least one population mean is different

17. The Limitations of the Test
ANOVA is appropriate whenever you want to test the significance of a difference across three or more categories of a single variable
This application is called one-way analysis of variance
Since we observe the effect of a single variable (age) on another (support for capital punishment)
Or effects of region of residence on TV viewing
But, the test has other applications
You may have a research project in which the effects of two separate variables (e.g., age and gender) on some third variable were observed (a two-way analysis of variance)

18. Limitations, continued
The major limitations of ANOVA are that it requires interval-ratio measurement for the dependent variable and nominal or ordinal for the independent, and roughly equal numbers of cases in each of the categories
Most variables in the social sciences are not interval-ratio
The second limitation is sometimes difficult, since you may want to compare groups that are unequal
So may need to sample equal numbers from each group

19. Limitations, continued
The second major limitation is that ANOVA does not tell you which category or categories are different if the null is rejected
Can sometimes determine this by inspection of the sample means
But you need to be cautious when drawing conclusions about which means are significantly different