Class Notes (806,583)
POL101Y1 (1,114)
Lecture 9

# POL101Y1 lec9.docx

4 Pages
102 Views

School
University of Toronto St. George
Department
Political Science
Course
POL101Y1
Professor
Jeffrey Kopstein
Semester
Fall

Description
POL101Y1 November 5 , 2012 Lec#9 -Experiments in Democracy-  Use experiments to understand why people vote an others don’t , etc…  Milk or tea first? / Mr. Fisher, Muriel Bristol – 8 cups of tea half milk first, half tea first/ she identified all 8 cups correctly.  Fisher exact test  The probability that she could get all the cups correct, by chance, is 1 in 70  We can learn from experiments, we can test peoples claims, treatment and control, randomization, measurement Game Plan  Some important questions… what do we mean by experiment? And why do we do them  Types of experiments-federalism and representation - clientalism and voting Important questions  Does federalism lead to better political representation  Are voters superficial?  How do we stop patronage and instead get public goods  Does contact from political campaigns matter in elections Defining experiments  Treatment/ conditions  Assignment to treatment or control/ comparison groups is random and the process of randomization is known  Ex-post measurements of results  Ex. Does Prof. Kopstein teach better when he wears a tie Treatments  A treatment is a stimulus  Anything that is thought to have an effect on some outcome  It is applied at some times and not others  Or it is appliead at some times and not others  Ex. Whether Prof Kopstein wears a tie to class to teach Random assignment  We put some subjects in treatments and some in control  We do it randomly  Ex. We could flip a coin before every class to se whether Prof. Kopstein would wear a tie Ex post measurement of results  For an experiment to be complete we need to measure results  To make a causal inference, we must have all three parts Measuring effects  What is a causal effect  Difference in outcomes between two states of the world, treated versus untreated  Ti=Yi (treated)- Yi (class with no tie)  Ti=Yi (class with a tie) – Yi (class with no tie)  Why is this problematic  We cannot observe any given subject in both its treated and untreated state  Fundamental problem of causal inference  Random assignment enables us to create two groups whose treated and untreated states are the same in expectation Why do an experiment?  Because we want to make causal inferences  We want them to be about important questions  Does federalism increase representations  Are elections won for superficial reasons
More Less

Related notes for POL101Y1

OR

Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Join to view

OR

By registering, I agree to the Terms and Privacy Policies
Just a few more details

So we can recommend you notes for your school.