STAT151 Lecture Notes - Lecture 14: Statistical Unit, Randomized Experiment, Dependent And Independent Variables

• School: University of Alberta
• Department: Statistics
• Course: STAT151
• Professor: Omar Rivasplata

Document Summary

In an observaional study, researchers don"t assign choices; they simply observe them o o. The text"s example looked at the relaionship between music educaion and grades. Since the researchers did not assign students to get music educaion and simply observed students in the wild, it was an observaional study. Because researchers in the text example irst ideniied subjects who studied music and then collected data on their past grades, this was a retrospecive study. Had the researchers ideniied subjects in advance and collected data as events unfolded, the study would have been a prospecive study. Observaional studies are valuable for discovering trends and possible relaionships. However, it is not possible for observaional studies to demonstrate a causal relaionship. An experiment is a study design that allows us to prove a cause-and-efect relaionship. An experiment: manipulates factor levels to create treatments o o. Compares the responses of the subject groups across treatment levels.