STAT 2080 Lecture Notes - Lecture 12: Probability Distribution, Sample Space, Stratified Sampling
Document Summary
Even if there is a strong association between explanatory variable and response variable, it does not always mean that explanatory variable (x) will cause changes in response variable (y) We often want to establish that changing x causes change in y. A strong association between y and x can be result of: Causation: some associations are explained by a direct cause-and-effect link between the variables, ex: direct causation: positive associations. X = mother"s bmi y = daughter"s bmi. X = amount of the artificial sweetener in a rat"s diet y = count of tumours in the rat"s bladder. X = alcohol consumption y = lung cancer risk: but, when when direct causation is present, very often it is not a. Complete explanation of an association between two variables: best evidence for causation comes from experiments that actually change x while holding all other factors fixed. So, if y changes, then we can say x caused changes in y.