Two Sample T-Tests

Copyright © 1997 by Forrest W. Young.

Two Independent Samples


  • Chapter 10 presents T-Tests for the situation where there are two completely separate samples that are independently taken from two different populations. Different subjects are used in each sample, and they are in no way matched with each other. There does not need to be the same number of subjects in each sample (i.e., sample sizes can be different).

    This situation is probably the most common experimental design in Psychology. These designs are sometimes called between-subjects or between-groups designs.

  • T-Test for Two Independent Samples
    Once again, the generic formula for the T-Statistic is:

    For the Independent Samples T-Statistic:

    1. Sample statistic: For Independent samples the sample statistic is the difference between the two sample means.
    2. Population Parameter: The population parameter is the hypothesized difference between the two population means.
    3. Estimated Standard error: The estimated standard error is defined as:

      This formula for the estimated standard error uses the "pooled" (combined) errors for the two sample means. The formula for this is:
    4. Independent Samples T-Statistic: Finally we can see how the T-Statistic for independent samples is defined:
    5. Hypothesis Testing: Hypotheses are constructed just as before, except that they are about the differences (usually involving hypotheses about zero differences). There can be one-tail tests, but usually, tests are two-tailed.

    Dependent Samples T-Test Example: Reading Ability


    We use data concerning reading ability. (These data are from page 543 of Moore and McCabe.) The data come from a study in which an educator tested whether a new directed reading activity help elementary school pupils improve their reading ability. The two groups are a classroom of 21 students who got the activity (the "Treatment" group), and another classroom of 23 students who didn't (the "Control" group). All students were given the Degree of Reading Power test.