PSY 313 Lecture Notes - Lecture 5: Blind Experiment, Statistical Power, Confounding
Document Summary
Between | independent measures experimental design: each participant receives 1 level of the iv. Subjects are randomly placed in only 1 group (control, treatment 1, treatment 2) comparison of groups tells us about effects of treatment: each individual score represents a unique individual variability of scores reflects individual differences. Clean measures no practice/fatigue effects and participants are na ve. Can ask who questions (allows for individual differences = individual differences = quasi-experimental design) Risk differences between participants in each group that are not related to iv - dealing with individual differences. Potential confounds: individual differences, assignment bias, environmental variables. But what if you assume everyone is same and ignore individual differences: use a controlled difference study - eliminate/minimize differences between groups, use experimental control (matching, holding constant, random assignment) Before-after design (pre-test post-test: test before and after the iv manipulation, measure difference and compare across groups. After-only design: measure only after an intervention/experiment, disad.
