Sample quality is relative. Can always say "you should studied population X" & no matter how good the sample, it's now biased wrt that pop.
@MichelleNMeyer @seanjtaylor But big diff between class-based non-random (political-id + frequent use) and imperfect random while attempting
-
-
@zeynep@seanjtaylor true, but what were alternatives? Could use what self-ID pol users post to create predictive algorithm of ideology? -
@MichelleNMeyer@seanjtaylor 1-FB already imputes political ID (check why I'm seeing this ad) so can test with non-declarers to check.
End of conversation
New conversation -
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.