You are on page 1of 4

# ANOVA and Multiple Comparisons in SPSS

STAT 314

Three sets of five mice were randomly selected to be placed in a standard maze but with different color doors. The response is the time required to complete the maze as seen below. Perform the appropriate analysis to test if there is an effect due to door color. (Use = 0.01)
Color Red Green Black 9 20 6 11 21 5 Time 10 23 8 9 17 14 15 30 7

1.

Enter the time values into one variable and the corresponding sample number (1 for Red, 2 for Green, 3 for Black) into another variable (see figure, below). Be sure to code your variables appropriately.

2.

Select Graphs Boxplot (Simple, Summaries for groups of cases) with the variable measured (Time) and the category axis variable (Color) entered (see figures, below). Click OK.

3.

Your resulting side-by-side boxplots will appear (see figure, below). As long as the boxes have approximately the same shape, you may continue with the ANOVA procedure.

4.

## Select Analyze Compare Means One-Way ANOVA (see figure, below).

5.

Select Maze Time as the dependent test variable, select Door Color as the grouping factor, and click Post Hoc. Select the Tukey procedure, enter 0.01 for the significance level (99% CI corresponds to a 1% (0.01) significance level), and click Continue. Click the Options button and select Homogeneity-of-Variance (checks assumption of equal variances). Click Continue to close the options and then click OK. (See the 3 figures, below.)

6.

## Your output should look like this.

7.

You should use the output information in the following manner to answer the question.
Step 0 : Check Assumption of Equal Variances (Homogeneity of Variances) The boxplots appear to be similar in size, so the variances are not significantly different. Also, the Levene Statistic p-value = 0.538 is greater than = 0.01 (from Step 2), so we fail to reject the null hypothesis that the variances are all equal. Since the variances appear to be equal (and we have random/independent samples), we may continue with ANOVA. Hypotheses

Step 1 :

## Step 2 : Step 3 : Step 4 :

Significance Level = 0.01 Critical Value(s) and Rejection Region(s) Reject the null hypothesis if p-value 0.01. Construct the One-way ANOVA Table

## p - value = Sig. = 0.0002

Step 5 : Step 6 :

Conclusion Since p-value = 0.0002 0.01 = , we shall reject the null hypothesis. State conclusion in words At the = 0.01 level of significance, there exists enough evidence to conclude that there is an effect due to door color.

8.

Since we rejected the null hypothesis (we found differences in the means), we should perform a Tukeys W multiple comparison to determine which means are different. Using the previous output, here is how such an analysis might appear.

Thus, we are 99% confident that mazes with green doors seem to take longer to complete than do mazes with Red or Black doors.

This table corresponds to our diagram. Note that the Black and Red means (8.00 & 10.80) are grouped together (separately from the differing Green mean (22.20)).