Please register to participate in our discussions with 2 million other members - it's free and quick! Some forums can only be seen by registered members. After you create your account, you'll be able to customize options and access all our 15,000 new posts/day with fewer ads.
Statespoll.com and Strehlspresdentialelection called the election 99 percent correct doing this.
State polling when weighed correctly looks the same for Trump in 2020
I'll answer this in all seriousness. While 'weighting' is an attractive idea and can, in some cases, improve the accuracy, the confluence of factors that probably would have made it more accurate to weight by these factors last time may not apply this time.
That is, it was probably an outlier that party ID correlated SO strongly in 2016, that so many polled did not respond with their true preference (the "shy Trumper" theory), and we had multiple outliers. It is far from clear that 'weighting' for these items will yield more correct results in this election, and generally weighting should be reserved for factors that are absolutely known to consistently have a direct impact on the final result. They impacted last time. Will they this time? How do you know?
It's the continued use of the term 'correctly' that make me wonder if people have really looked into the methodology of pollling. 'Weighted correctly' seems to mean, to those using it, weight it in such a way my preferred candidate's results appear better. They truly believe that's reality-that the weighting will show a more accurate result. But experience tells us it probably won't, and we can already predict if President Trump doesn't win, his supporters will consider it a 'rigged election.'
See below link and text from it for a more in-depth discussion. I bolded/highlighted some key points.
"Bad Weighting: The most common bad weighting in political polls is weighting just the likely voters for the number of Democrats, Republicans and others. Party identification is correlated with voting, but what is missing are meaningful numbers of party members for the whole population. Without that, the weighting is a guessing game rather than good theory. Some pollsters use the numbers from an exit poll from a past election, but the numbers of people who consider themselves members of a party changes from month to month and year to year.
Consider the change in party identification from the Pew Research Center polls throughout 1996. In the beginning of the year the Republican-Democrat split was 30%-30%. On Election Day it was 26%-36%. The number who considered themselves Republicans went down steadily the closer the survey was to the election. Using party identification to weight just the likely voters in a political poll is little better than a guessing game where the pollster is substituting his or her judgement for scientific method.
Another type of bad weighting for elections polls occurs when the weighting characteristic has a low correlation with key variables such as voting. For example, in some elections there may be no relationship between age and voting. If the age-voting relationship is weak then weighting for age will make the sampling error larger. Sometimes there is a strong relationship with vote but a weak relationship with some other characteristic. That other characteristic will have a larger sampling error. One also should avoid weighting that creates a large discrepancy in the weights applied to different sample cases."
I was confused what you were talking about, as a slight majority of scientifically conducted polls show Biden leading. Then I read the links and realized, oh, they're 'weighted polls.' In other words, polls adjusted by rabid partisan hacks to show their preferred candidate leading. Got it. I posted a link in this thread that puts 'weighting' to complete bed as the complete ignorant idiocy it is:
I am totally enjoying the meltdown you are having over actually being behind in the polls, and it would be very satisfying to me if your preferred candidate loses so you can cry about how unfair it is. But keep hoping. As we said in the Army, hope is not a method.
Matchroad is about the 20th re-registration Westie15. In his various iterations he has incessantly posted links to either that website or one called statespolls.com (or something similar) both of which re-weigh polls according to how whoever runs those websites thinks they really should be weighed. I'm starting to wonder if Westie15 and all his 20-ish iterations are actually the guy in those websites, and one of his reasons for being here is to promote his website.
But this iteration will get banned soon enough, just like the previous 20, and his posts will disappear, so you can effectively ignore his posts.
Please register to post and access all features of our very popular forum. It is free and quick. Over $68,000 in prizes has already been given out to active posters on our forum. Additional giveaways are planned.
Detailed information about all U.S. cities, counties, and zip codes on our site: City-data.com.