POL222H1 Lecture Notes - Lecture 10: Instrumental Variable, Federal Assault Weapons Ban, Spurious Relationship
Document Summary
Calculate the average of y for each value of x. Instead of matching observations based on the values of each. Z, we may match them based on a summary measure of similarity of all z"s. Alternative method to control for confounding variables when x is a dichotomous variable (x=1 or x=0) We say an observation is in a treatment group if x = 1 or a control group if x = 0. For each observation in the treatment group, we match an observation in the control group which shares the same or similar value of z. Value of z will be held constant, on average, between the treatment and the matched control groups. May be some observations in control group which are not included because don"t have same values as confounding. Or may be some which were used multiple times in order to match. Value of z held constant between both groups.