POL222H1 Lecture Notes - Lecture 3: Grater, Confounding, Spurious Relationship
Document Summary
Pol222 how to evaluate causal relationship: reverse causality and simultaneous relationship, confounding variables, bivariate relationship between x and y. X causes y: we should consider whether there is possibility what could cause x. Is there causal mechanism in which crime rate can increase or decrease. Independent variable x dependent variable y: e. g. , college education political participation, causal argument = people will have greater information, college education is likely to increase for political participation, z political participation. If there is a relationship between x and z , z is called a cofounding variable. If there is a certain relationship between x and z which also causes y, then it is a confounding variable: focus on x z, x y, z y. B* = b+(y x a) (y x a) is the bias from omitting the confounding variable: spurious relationship: no 2 relationship between x and y so b= 0.