1. Bigger sample is not always better – one ofthe worst statistical mistakes ever made in the history ofstatistics happened in the 1936 U.S. Presidential Election. Theincumbent president Franklin Roosevelt of the Democratic Party andAlf Landon of the Republican Party are the two main presidentialcandidates. Look the event up at this webpagehttp://www.math.upenn.edu/~deturck/m170/wk4/lecture/case1.html andanswer the following questions.

1. Find the Literary Digest’s pre-election prediction forRoosevelt and Landon, in percentage of popularity vote. (Onepercentage for Roosevelt and one for Landon.)
2. Find the 1936 Presidential election result for Roosevelt andLandon, in percentage of popularity vote.

(One percentage for each.)

1. Find the sample size used by Literary Digest.
2. The Literary Digest’s sample has a problem with the selectionbias. Identify the target population, sampling frame and brieflyexplain why there was a selection bias.
3. The Literary Digest’s sample also has a problem with thenon-response bias. Report the number of surveys sent, number ofsurveys received, and calculate the non-response rate (in %).
4. The Literary Digest’s sample has a problem with the responsebias. Mind you that the US is in their eighth year of the GreatDepression. Briefly explain how the Great Depression has anythingto do with the response bias.
5. Find the sample size used by George Gallop.
6. What was his (George Gallup’s) pre-election prediction forRoosevelt, in percentage of popularity vote? (Please look thisquestion (h) up on the internet. The numbers may vary fromdifferent sources or web sites. Just pick one and it will not bemarked based on the accuracy of the numbers.)