Exercise 3: Trying out a T-Test

exercise 3

3. Results

If we look at the Independent Samples Test box, we see several more pieces of information.

Before looking at the results of the t-test, we see Levene’s test. This gives us an idea of how similar the variances of the groups are. If the variances are too acceptably low, we follow the Equal variances assumed (top) line of results. Sig. is the p-value associated with Levene’s test. It is much higher than usual critical values (e.g. 0.05) so we do not reject the null hypothesis that the variances are equal – i.e. we assume they are. The t-test is therefore not compromised on these grounds.

We can therefore follow the top line of the results. What is the t-statistic? The Sig. is the p-value for the test – giving the probability that this t-statistic would arise under the conditions of the null hypothesis. SPSS gives it as .000 as shorthand for it being less than .001. We can therefore reject the null hypothesis.

Now try running the test using ADIPOSITY instead of BODYFAT. What are the null and alternative hypotheses? Should you reject the null hypothesis? What does the test tell you? Does this conform to your expectations, given the boxplot results?