SOAN 2120 Lecture Notes - Lecture 8: Dependent And Independent Variables, Blind Experiment, Experiment

• School: University of Guelph
• Department: Sociology and Anthropology
• Course: SOAN 2120
• Professor: D Walters

Document Summary

Independent variable > dependent variable (differences in outcomes between two groups) *scores on all other variables which are likely to affect the dependent variable. *the objective is to give equal probability to each participant of being assigned to the experimental or control group. This is essential if we want to say that the differences after the experiment are due to the manipulation. Even with random assignment, the two or more groups will not be exactly equal in all respects. If the assignment is random, we can use our tests of statistical signi cance (manipulation versus random variation) As n increase, individual differences between the groups decline (law of large numbers tells us this) Without ra: our ndings may be attributable to pre-existing differences between the groups. We could compare pre-test scores (dependent variable measures) before the experiment begins. *if they"re equivalent, we could proceed as if ra had taken place. But ther confounding variables are dealt automatically with ra.