Wading Through the Data Swamp:
Program Evaluation 201

Module 5: The t-Test of Difference Between Means - Page 14 of 24

So, Are the Participants and Comparisons Comparable Regarding Inhalant Use?

As shown in steps 10 and 11, we fail to reject the null hypothesis of no differences. In simple English, it means that the mean for inhalant consumption of participants before the Cool After School Program is not different from the mean for inhalant consumption of the comparison group at the 0.5 level of significance.

This is great news. Since the participant group and comparison group were not statistically different at pretest, we can now compare the posttest scores for the participant and the comparison groups using a t-test.

A picture of an atom.

The Importance of Baseline Equivalence

When two groups are not equivalent at baseline, it is unfair to compare them after the program. You cannot conclude that any differences are the result of the program. If the groups are different, changes may occur for reasons other than the program. It's like comparing apples and oranges.

<< Previous Page Next Page >>