Literary Digest Poll

1
Literary Digest Poll

• 1936 election Franklin Delano Roosevelt vs. Alf
  Landon
• Literary Digest had called the election since
  1916
• Sample size 2.4 million!
• Prediction Roosevelt 43
• Actual Roosevelt 62
• (Literary Digest went bankrupt soon after)

2
What went wrong?

• Context
• 9 million unemployed real income down 1/3
• Landon Cut spending versus Roosevelt
  Balance peoples budgets before governments
  budget
• Polling
• Survey sent out to 10 million people from
  subscription list, telephone directories, club
  membership lists
• 2.4 million responded

3
Sources of bias

• Sampling frame not representative
• Biased toward better off groups (and more
  Republican)
• Voluntary response bias
• The anti-Roosevelt forces were angry---and had a
  higher response rate!

4
George Gallup did it right

• Roosevelts percentage
• Actual election result 62
• Literary Digest prediction 43
• Gallups prediction of the Digest prediction
  (based on sample of 2,000) 44
• Gallups prediction of the election result (based
  on sample of 50,000) 56
• Gallup used Random sampling

5
The Year the Polls Elected Dewey

• 1948 Harry Truman (Dem) vs. Thomas Dewey (Rep)
• All major polls predicted Dewey would win by 5
  percentage points (even Gallup)

6
What went wrong?

• Quota Sampling
• Each interviewer assigned a fixed quota of
  subjects in certain categories (race, sex, age)
• In each category, interviewers free to choose
• Left room for human choice---and inevitable bias
• Republicans were easier to reach
• Had telephones, permanent addresses, nicer
  neighborhoods
• Quota sampling abandoned for Random Sampling