Polls and Elections: The Chicago Record Poll and the Election of 1896

Abstract

The Chicago Record poll of the presidential election of 1896 was an enormous, multistate mail survey. Unfortunately, its results were incredible. The newspaper attempted to correct the results, making perhaps the first ever attempt to deal with nonresponse bias, but did not have much success. Had responses been properly corrected for differences in response rate, the poll would have generated a satisfactory set of predictions.

Shy Trumpers and Live Callers : An Analysis of The U.S. 2020 Polls

“…Instead, they find the main reasons for error to be unrepresentative samples and weighting, and late-deciding voters. Thies [16] shows that, when properly weighted, the Chicago Record Poll of 1896 would have delivered useful forecasts of that year's Presidential election in spite of massive non-response bias 2 .…”

How the American Public Perceived Electoral Competition in the States during the Pre-poll Era: A Prediction Market Data Analysis of the 1896 Presidential Election

“…The use of election returns data is a limitation in historically oriented research because it is not clear if the changes in partisan coalitions result from voters switching parties, dealignment or mobilization-this is inferred from election results, whereas research based on poll data can find out directly from the public if voters switched parties, did not vote, or recently joined the electorate. Though there was some polling done during the 1896 election (Thies 2018), it was before the advent of scientific polling. And so, absent from this extensive electoral history are the voices of the people.…”