In 1936, Franklin Delano Roosevelt [Democrat] had been President for one term. The magazine, The Literary Digest, predicted that Alf Landon [Republican] would beat FDR in that year's election by 57 to 43 percent. The Digest mailed over 10 million questionnaires to names drawn from lists of automobile and telephone owners, and over 2.3 million people responded - a huge sample.? ? ? ? ? ? ? ?At the same time, a young man named George Gallup sampled only 50,000 people and predicted that Roosevelt would win. Gallup's prediction was ridiculed as naive. After all, the Digest had predicted the winner in every election since 1916, and had based its predictions on the largest response to any poll in history. But Roosevelt won with 62% of the vote. The size of the Digest's error is staggering. How could they have been so far off?
The Literary Digest had made two fatal mistakes. Their list of names was biased in favor of those with enough money to buy cars and phones, a much smaller portion of the population in the thirties than it is today. And, more seriously, the Digest had depended on voluntary response. FDR was the incumbent, and those who were unhappy with his administration were more likely to respond to the Digest survey.[The magazine folded, not too much later; some think the wrong prediction was largely responsible. Gallup's scientific polling organization still exists, highly respected for the quality of their work over almost 70 years.]When a sample is biased, a large number of subjects cannot correct for the error.
| Sievers home | Math151-Sp04/Litdigest.htm | 3pm | 3/17/04 |