PSYC209 Lecture 10: Testing Means - Related Samples
Document Summary
Samples in which the participants are observed in more than one treatment or matched on common characteristics. Two types: the repeated-measures design, the matched-pairs design. We measure a dependent variable for participants observed before (pre) and after (post) a treatment: within-subject design. We observe participants across many treatments but not necessarily before and after a treatment. Participants are selected and then selected, experimentally or naturally, based on common characteristics or traits. Can be obtained in two ways: experimental manipulation. Requires that you measure some traits or characteristics before we match participants into pairs: natural occurrence. Typical for quasi-experiments in which participants are matched based on preexisting traits. First we subtract one score in each pair from the other to obtain the difference score for each participants; then we compute the test statistic. It eliminates the source of error associated with observing different participants in each group or treatment.