STATS 13 Chapter Notes - Chapter 4: Blind Experiment, Near-Sightedness, Observational Study
Document Summary
Ex. smokers have higher rates of lung cancer. Cannot prove that lung cancer is caused by smoking. Variable that is related to both the explanatory and the response variable. Effect on the response variable cannot be separated from the effect of the explanatory variable. Gene that makes people more likely to smoke and likely to get lung cancer. Association is necessary to prove causation but association alone is not enough to prove cause and effect. Two variables are associated if the value of one variable gives you information about the value of the other variable. When comparing groups, the proportions or means take different values in the groups. Ex. whether or not a sleeping with the light on as an infant caused nearsightedness. Is impacted or changed by the explanatory variable. Confounding variables prevent us from being able to draw conclusions about a cause. Good studies avoid the effect of confounding variables.