Lab #6 Preview
Independent Samples t Test
Purpose
Compare the sample means for two different groups of individuals (aka a “between-subjects” design). Is there a significant difference between the groups?
For our lab, the question is about a sample of nurses, some working in a hospital setting and others working in an office setting. We want to determine whether hourly salaries differ for the two groups of nurses.
Group 1: Nurses at Hospital compared to Group 2: Nurses at Office
Grouping variable (IV or quasi-IV):
- position (0 = work in hospital setting, 1 = work in office setting)
(this lab also analyzes age range groups; you can see how that variable is coded in the Variable View!)
Measures (DVs):
- hourwage (a continuous scale variable of hourly salary earned)
Null Hypothesis: Mean salary for hospital nurses = Mean salary of office nurses
Alternative Hypothesis: Mean salary of hospital nurses ≠ Mean salary of office nurses
Levene’s Test is a preliminary test to determine whether the groups have equal variances. It is used to select between two versions of the independent samples t-test. SPSS produces both t-tests (one for equal variances, the other for unequal variances), you choose the correct one!
Independent samples t-test is a test of the null hypothesis. Based on test results, we either:
- Reject the null hypothesis (and conclude there is likely a difference in the means), or
- Fail to reject the null hypothesis (and conclude the means do not differ significantly)
APA Style
APA style has a standard way to report hypothesis testing results. For an independent samples t-test you need to report the means and standard deviations of the two samples. You’ll also need to say whether the results were “significant” (when you can reject the null) or “not significant” (when you fail to reject the null) in your wording and make conclusions about a mean being smaller, bigger, not different, or whatever makes sense and is supported by your analysis! You would then also, at the end of your sentence(s), add what I call “the t statement”, which notes the calculated t-value, the degrees of freedom (always in parentheses after the t symbol), the p-value, and the effect size as is shown in the examples below. For the p-value, you can report either the exact value as given in SPSS or that the p is < or > .05, assuming that .05 is our chosen alpha value. For different examples (with made up numbers), you might see something like either of the following to report an independent samples t-test in APA Style:
- The average intelligence score of science majors was 112.25 (SD = 15.3) which was significantly higher than the 105.36 (SD = 14.9) average intelligence score for humanities majors, t(82) = 2.45, p = .032, d = .45.
- The female basketball players were not significantly taller (M = 71.3 inches, SD = 3.4) than the female volleyball players (M = 69.8, SD = 4.2), t(38) = 1.77, p > .05, d = .38.