To assess whether a new bootcamp regimen increases BMI, BMI measured for 15 clients before and after. Which test is appropriate?

To assess whether a new bootcamp regimen increases BMI, BMI measured for 15 clients before and after. Which test is appropriate?

• A. Matched-Pairs T-Test
• B. Two-Sample T-Test
• C. One-Sample T-Test
• D. Proportion Z-Test

Answer: (A)

When you have two related measurements on the same people, you compare the average change within individuals. For BMI before and after a bootcamp on the same 15 clients, use a matched-pairs (paired) t-test. It analyzes the differences for each person (post minus pre) and tests whether the mean difference is significantly different from zero, which directly answers whether BMI tends to increase. This approach accounts for individual variability and the dependence between the two measurements. The calculation hinges on the mean of the differences and their standard deviation, then forming a t-statistic with the number of paired observations. With 15 subjects, the paired t-test is appropriate as long as those differences are roughly normally distributed. The other options don’t fit: a two-sample t-test assumes independent groups (pre and post from different people), a one-sample t-test tests a single sample against a constant value, and a proportion z-test is for binary data, not a continuous measure like BMI.

When you have two related measurements on the same people, you compare the average change within individuals. For BMI before and after a bootcamp on the same 15 clients, use a matched-pairs (paired) t-test. It analyzes the differences for each person (post minus pre) and tests whether the mean difference is significantly different from zero, which directly answers whether BMI tends to increase. This approach accounts for individual variability and the dependence between the two measurements. The calculation hinges on the mean of the differences and their standard deviation, then forming a t-statistic with the number of paired observations. With 15 subjects, the paired t-test is appropriate as long as those differences are roughly normally distributed. The other options don’t fit: a two-sample t-test assumes independent groups (pre and post from different people), a one-sample t-test tests a single sample against a constant value, and a proportion z-test is for binary data, not a continuous measure like BMI.