Imagine the Biology department needs to decide which lab curriculum yields better student outcomes. Five sections are assigned to curriculum A, and five sections are assigned to curriculum B. All sections are administered a pre- and post-test that measures students’ attitudes toward science and knowledge of biology. The department wants to see if students’ gains are greater in one curriculum or the other.
What statistical test should be done to determine if there is a significant difference? Explain why you chose this test.
Answer: Paired T-test
Explanation
We have been given two data sets: one for the pre-test results and one for the post-test results. Moreover, the data are paired, because we have two data values (pre-test and post-test) per section.
In this case, we are then interested in performing a paired t-test (which is basically a t-test for one population on the data set of the differences between each pair pre-post). The paired t-test uses the Student T-distribution, which is why it is called the t-test.
Moreover, the test will allow us to test whether there are any significant differences between the pre-test and the post-test results. If the P-value is sufficiently small (generally, smaller than 0.05), then we conclude that there is a significant difference.
