Post

Looks like the data is bad. They surveyed equal numbers of each political type and averaged the results. www.kff.org/coronavirus-...

There are way more Democrats than Independents, for example, so there’s no way they should be weighted equally if you want to draw conclusions about the whole US population. I suspect their other data is similarly flawed.

Here it is. You can’t project across the entire population when your sample is improperly weighted. www.kff.org/report-secti...