Econometrics: A survey of 1000 registered voters is conducted, and the voters are asked to choose?

Econometrics: A survey of 1000 registered voters is conducted, and the voters are asked to choose?




A survey of 1000 registered voters is conducted, and the voters are asked to choose between candidate A and candidate B, Let p denote the fractions of the voters in the 'population' who prefer candidate A, and let pˆ denote the fraction of voters in the 'sample' who prefer candidate A. In the survey, 650 voters responded that they would vote for candidate A and 350 responded that they would vote for candidate B.



a. Use survey results to estimate p.



b. Using pˆ(1-pˆ)/n as an estimator for the variance of pˆ and find the standard error of the estimator.



c. Set up a two-sided hypothesis test that investigates if candidate A is 3 times more likely to win compared to candidate B at the time of the survey. Write down the null and the alternative hypothesis (hint: Either candidate A or candidate B can win the elections thus the sum of their winning probabilities is equal to 1).



d. Calculate the t-stat of the test and report the results of the test at 5% significance level.





No Answers Posted Yet.