Nov 1, 2016
Researchers used the RAND Presidential Election Panel Survey to estimate the popular vote in the U.S. election and determine which candidate Americans think will win.
The RAND 2016 Presidential Election Panel Survey (PEPS) uses a unique approach to study the evolution of public opinion, voting intentions, and voter behavior.
Rather than surveying a new cross section of respondents each survey, PEPS contacts the same respondents over the course of the election cycle.
PEPS uses the ongoing RAND American Life Panel (ALP) survey, which allows responses to be linked to previous surveys on voter intentions, opinions, behavior, and life circumstances.
The ALP consists of a panel of U.S. respondents ages 18 and older. Respondents complete surveys on the web, however, in contrast to most Internet panels, ALP respondents are supplied with Internet access if needed, so the panel represents the entire U.S. adult population.
PEPS includes a subsample of 3,000 ALP members, who are asked about their opinions about political issues in the news, attitudes towards potential candidates, voting intentions, candidate preferences, underlying attitudes towards societal groups, political affiliation, prior voting behavior, and perceived personality traits of candidates and the respondents themselves.
The PEPS methodology has two primary advantages over traditional polling.