T-tests are a special type of inferential statistic used to compare two different means to each other. The t-test produces a t statistic that is a ratio of the difference between the means being compared to the variability of the observations within each set of data on which the means are based. An independent samples t-test can be used to compare two means taken from different groups (resulting from a between-subjects design). The matched-samples (also called a paired-samples or dependent) t-test can be used to compare two means taken from the same group of subjects under two different conditions (resulting from a pre-post test or within-subjects design).

Consider an experimental study of the effect of over-learning on memory in college students that uses a between-subjects design. When we use over-learning, we study material until we know it perfectly, and then continue to study it some more. At the beginning of the experiment, the participants would be selected from the same population (college students) and randomly assigned to either the experimental group (over-learning) or the control group (normal studying). Thus, the independent variable would be the method of studying (over-learning versus normal studying). The dependent variable might be the score on a 100-point exam on the material studied. These data would most appropriately be analyzed with an independent samples t-test.