POL101Y1 Lecture Notes - Lecture 20: Causal Inference, Ronald Fisher, Exact Test
Document Summary
Milk first to cool down tea to prevent cracking the china tea cup. All characteristics we need today in political science. Obviously , this is why today we know about this example. The probability that she could get all the cups correct, by chance, is 1 in 70. Treatment , political world, affects outcome i. e. free tuition for a year randomly / suppose we understand how to let people vote / etc. For an experiment to be complete , we need to measure the results. What we want to measure are causal effect. Treatment :suppose he always wore a tie ( wearing a tie) Assignment : flip a coin before class ( prof. hansen decided on his own when to wear a tie ) To have an experiment ,we must have all three parts. To make a causal inference , we must have all three parts. Difference in outcomes b/w two stated of the world : treated vs. untreated.