PSY 200 Lecture Notes - Lecture 11: Mean Absolute Difference, Internal Validity, Variance
Document Summary
Chapter 11: the t-test for two related samples. Last week, we talked about the indpt t-test- for between subjects designs. Comparing one person at two time points is called a within subjects design. Two separate scores are obtained for each individual in the sample. Same subjects are used in both treatment conditions. No risk of the participants in each treatment group differing significantly from each other. Reduces or eliminates influence of individual differences. Factors besides treatment may explain differences (i. e, history, attrition) Participation in first treatment may influence score in the second treatment (order effects) Repeated-measures t-test used for within- subjects design. Independent variable: must be nominal and dichotomous. So, it"s a group of only two levels i. e. time 1 and time 2. Dependent variable: only one, and must be interval or ratio. Distribution of difference scores (d values) must be normal. With relatively large samples (n > 30) this assumption can be ignored t statistic for repeated measures.