In 2016, polling was fatally flawed especially in the US general presidential election. One mistake was in sample selection.

At least one 2020 DNC primary election poll has had statistically insignificant samples to represent those under 50, which makes me wonder how much has really changed since 2016.

I would be interested to find metadata on primary and general election polls in 2016 and primary election polls in 2020. Specifically metadata on sampling selections and other polling features that may indicate if and how polling methods have changed or remain flawed.

Data for the expected 2016 and 2020 voter demographic turnout would also be useful to see how representative the polling sample selections are.

  • Polling was not "fatally flawed". it predicted a 70% win chance for Hillary and a 30% chance for Donald Trump. Predictions like this are supposed to be wrong 3 out of 10 times, that's what 70% and 30% mean.
    – user3856
    Jun 24 '19 at 17:45
  • @BarryCarter Good sample selection is essential for statistical methods to accurately make predictions. If the sampling was realistic, then your comment would be reasonable. A failure to poll a significant portion of the largest voting block (Millennials), means such polls are not based on a good sample... Instead such polls are measuring the vote of older generations and predicting how they will vote. Jun 28 '19 at 15:50
  • Can you source that the random selection process itself was flawed, or at least flawed moreso than it normally is? (since it's surprisingly hard to get a random sample of voting Americans).
    – user3856
    Jun 30 '19 at 4:08

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.