Lecture 10 – Comparing Two Means – Summary Page
- t-tests – tell you whether the average score on a particular variable is significantly different across
- If there’s a difference between means, tell if it is significant.
- Parametric test (vs nonparametric)
a. One sample t-test
i. Testing whether the mean in one group is significantly different from a number
in a different group.
ii. Is there any actual difference between a certain point and the other mean being
b. Dependent samples t-test/Paired samples t-test
i. Cases are related – e.g., Before/after test
ii. Single sample, before and after test.
iii. Ie measuring before and after weight loss and gain starting herbal magic.
c. Independent samples t-test
1) Independent samples t-test
a. Tests for differences in the mean for 2 unrelated (“independent”) groups.
b. Ie difference between men and women, rural and urban, poor and rich
1. P-P, Q-Q, skew, kurtosis, histogram, MOCT
ii. Homogeneity of variance
1. Levine’s test.
iii. Independence of cases (except for the dependent/paired samples t-test
1. Different from independence of variables
2. Each case is different in the sample
iv. Interval level data
d. Equation – general form
variance 1 variance2