Reference no: EM132880083

1. Winning Lottery and Supporting Local Casino

A researcher wants to know how winning money from "scratch-off" lottery tickets affects people's views about allowing the opening of a casino nearby. People can buy as many tickets as they want; and, of course, some people don't buy any tickets at all. Lottery tickets cost $5, almost all tickets entail some prize, and prizes range in value from $1 to $200. The researcher interviews a random, representative sample of adults in the city and compares the attitudes of those who report winning more than $50 in the lottery in total over the past month to those who claim to have won little or nothing. The researcher reasons that the lottery chooses winners at random, and hence the amount that people report having won is random.

a) Think of the outcome variable as an individual's answer to the survey question "Are you in favor of allowing a local gambling casino to be built in our city?" Would the researcher's comparison between those who won more than $50 and less than $50 reveal a causal effect?(Write down "yes" or "no"

b) If your answer is "yes" in a), explain the randomization and the potential problems it overcomes. If your answer is "no" in a), explain what are potential problems with this comparison.

c) Same question as in (a), but now assume the researcher were to restrict the sample to people who had played the lottery at least once during the past month.

d) If your answer is "yes" in c), explain why restricting the sample solves potential problems in causal inference. If your answer is "no" in a), explain what are potential problems with this comparison.