Plus, the mistakes I made in the “data journalism” era.

Title is hyperbole. Essentially the answer is maybe but most likely not. Has a discussion about potential poll error in the context of precision vs. accuracy. Notes that the model assumes accuracy but not precision.

  • abff08f4813c@j4vcdedmiokf56h3ho4t62mlku.srv.us
    12·
    18 days ago

    For what it’s worth, the first sentence after the subscriber paywall is this,

    My short answer is “no”. Indeed, if I thought polling was predicatbly biased, I’d have built that into the model somehow.