The reason we adjust polls for the national trend is because **that's what works best emperically**. It's not a subjective assumption.
-
The problem is that we're doing this in a world where people—like
@ryangrim—don't actually give a shit about evidence and proof.
ur trend line adjustment was certainly theoretically defensible 18 mos. ago, but you can't ignore the wild effect it has had
-
-
: Very professional of you not bother asking me for comment ahead of time. So unbelievably lazy.
-
the piece links to your public reasoning. Happy to add any further explanation you want in there
-
: The article made clear you have **no fucking idea** what you're talking about. That's why you contract people **ahead of time**.
-
.
@NateSilver538 my hero Ultimate take down of a huffington post journo by a statisticianhttps://mobile.twitter.com/NateSilver538/status/795015340539473924 …
End of conversation
New conversation -
-
-
Ur argument is the equivalent of throwing a snowball at
@NateSilver538 and declaring climate change doesn't existThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
538 projections a lot closer to the pack for senate control, and they don't use natl trend line adj. Coincidence?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
trend line adj projects state polls when infreq using natl poll trend. But 2x counts trend when state polls freq!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thank you!! I said sameon Friday! Trend line adj has no place when state polls are frequenthttps://twitter.com/matthfink/status/794662880041910272 …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
.
@ryangrim@NateSilver538 Grim's art. pretends Nate isn't open book - tons of public explanatory mat'l. Lazy 2 say he's just making it up.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Article says Clinton has a comfortable lead in Florida. Not true. She might win due to turn out, demographics, but close race.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
So this is the kind of shitty journalism Huffpo has huh?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I have no dog in this fight, but this Grim person seems to not know what the F he is talking about.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
is that wild effect wrong? I'm honestly curious trying to learn this stuff. Why do you assume low volatility?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Hitlery rally: half a high school gym, Trump rally: 20,000+++ in a football stadium. BOTH of you are fucked up!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
He's following a model which has historical correlation. How do you want him to change the model and on what basis
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
you really do not understand the trend line adjustment. Maybe audit a stats class.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
What you're saying is that it was ok when it was helping your candidate, but not now that it's hurting her?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Why is this wrong,
@ryangrim ? You don't understand how probabilities work, do you?Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
do you like anal sex? Also do you pleasure yourself to pictures of Hillary? Or Anthony Weiner?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.