-
This Tweet is unavailable.
-
-
This Tweet is unavailable.
-
Replying to @PsychRabble @Noahpinion
If social desirability bias didn't have a big impact on responses to survey questions like this, maybe the pollsters would have predicted the 2016 election outcome?
3 replies 0 retweets 6 likes -
This Tweet is unavailable.
-
Replying to @PsychRabble @primalpoly
The models that predicted a certain Hillary victory were aggregators of state-level polls that (stupidly) assumed perfectly correlated state-level polling errors, if I recall correctly.
1 reply 0 retweets 3 likes -
It wasn't social desirability bias so much as an inability of the models to predict the case in which Trump outperformed in the places that mattered (Midwest) while Hillary outperformed in the places that didn't (CA/NY).
1 reply 0 retweets 5 likes -
Isn't that the opposite of what SDB would predict? Seems like social pressure to say you like Hillary would be much greater in CA/NY than the Midwest.
1 reply 0 retweets 0 likes
Good point. Hmm.
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.