Which test is parametric for comparing two related (dependent) samples?

Which test is parametric for comparing two related (dependent) samples?

• A. Paired samples t-test
• B. Unpaired t-test
• C. ANOVA
• D. Pearson's r

Answer: (A)

When you have two related measurements from the same participants (such as a pre-post design or matched pairs), you test whether the average difference between the two time points is zero. The paired samples t-test is designed for this situation and is a parametric approach because it relies on the differences between the paired scores being approximately normally distributed and measured on an interval or ratio scale. It evaluates whether the mean of those difference scores differs from zero, which directly answers whether there is a systematic change. The other option for two groups with one measurement each is for independent samples, which is not appropriate here because the data points are related. ANOVA can handle more complex designs or repeated measures, but for simply comparing two related samples, the paired t-test is the most straightforward parametric choice. Pearson’s r, on the other hand, assesses the linear relationship between two variables, not a mean difference between paired measurements.

When you have two related measurements from the same participants (such as a pre-post design or matched pairs), you test whether the average difference between the two time points is zero. The paired samples t-test is designed for this situation and is a parametric approach because it relies on the differences between the paired scores being approximately normally distributed and measured on an interval or ratio scale. It evaluates whether the mean of those difference scores differs from zero, which directly answers whether there is a systematic change.

The other option for two groups with one measurement each is for independent samples, which is not appropriate here because the data points are related. ANOVA can handle more complex designs or repeated measures, but for simply comparing two related samples, the paired t-test is the most straightforward parametric choice. Pearson’s r, on the other hand, assesses the linear relationship between two variables, not a mean difference between paired measurements.