Ricochet is the best place on the internet to discuss the issues of the day, either through commenting on posts or writing your own for our active and dynamic community in a fully moderated environment. In addition, the Ricochet Audio Network offers over 50 original podcasts with new episodes released every day.
Yes, there are ‘shy’ Trump voters who either don’t respond to polls at all, or perhaps even lie to pollsters, but that doesn’t affect poll results as much as the over-sampling of Independents for Biden.
How do Independents and non-affiliated voters get over-represented in every poll?
Polling companies know well Republicans are significantly less likely to respond to a poll. Their solution is to keep calling people’s homes screening for Republicans until they reach the goal of the model for the representative sample. We can assume that is sufficient for the soft science of polling.
But when the quota of Independents in the model is filled, polling stops.
For the sake of this discussion, it doesn’t matter what the actual modeling of R/D/I in the poll. Let’s say it’s 33/33/34. We are only looking at Independents.
If Trump-voting Independents are less likely to even respond to a poll, and Biden voting Independents are more likely to respond to a poll, then the Independent category gets filled quickly with more Biden voters. The polling company reached its quota for Independent voters in the sample. There is no consideration that the internals of this sample could easily be skewed towards Democrat leaners and away from Republican leaners on the basis of how differently the two groups are inclined to respond at all.
I believe it is a significant number.Published in