Polling

​Most mornings I listen to the Daily from the New York Times as I drink my coffee and work on my puzzles. Today, Michael Barbaro, was hosting and his guest was nationally renowned pollster, Nate Silver. I think that Michael had all the right questions but I think that Nate did not have all the right answers.
First, let’s recall that polling these days is a fraught enterprise. It is so because achieving an unbiased sample is nearly impossible to achieve. I have documented in this journal my concerns about the accuracy in polling (Presidential Polls and What to Pay Attention to, 8/19/2019). I stopped doing most public opinion polling years ago because of the sampling problem. Samples simply are not random because respondents are free to choose to respond or not. So, let’s remember this as we go forward thinking about polling results.
All elections are local. So, any shift in a national poll may not have any implications in changes for local results. In other words, if we are looking for how a specific race is going to turn out we need local numbers. The national trend is meaningless. If, for example, the shift in the national trend all came in states that were already leaning a particular way the shift would have no impact. You really need more information than the results of a national poll.
The part of the conversation between Michael and Nate that I found most interesting was when they were talking about the shift in the national poll from favoring Democrats in the summer to the fall poll showing a preference for Republicans. Really? The shift according to Nate was a 3% margin for Dems in the summer to a 1% margin for Republicans. Nate thought that was significant. I say poppycock!
Importantly the magnitude of the shift, what Nate called 4% is misleading. The shift is really only 2%. Imagine that the Dems were leading 51% to 48% and that shifted to 50% favoring the Republicans and 49% favoring the Dems. That result is achieved by a shift of 2% of the sample moving from Democrats to Republicans. All of this is well within the margin of error, which is to say there is no real difference here. Even if the numbers were accurate the difference would be effectively nil.
I think you need to take the results of current polls with a grain of salt. I also believe that you can’t apply national polling results to local elections. Think about it. Nationally Democrats have an overwhelmingly large portion of the population. But we know that because of our goofy electoral system and gerrymandering that there is a close balance of power between the national parties. National polls should show Democratic dominance but don’t. Why?