Absolutely use multiple imputation!
-
This Tweet is unavailable.
-
-
Replying to @karenerrichetti @ProfMattFox
I would've thought the fact that the data was missing might be more important than the score itself, no? For example, if FPG was missing it might be because it was too expensive for that person to get tested, which could be more important for prediction than their FPG value
1 reply 0 retweets 2 likes -
What if you added in a missing variable to the propensity model? That way you could included the imputation and the extra info about missing data
0 replies 0 retweets 3 likes -
This Tweet is unavailable.
-
Replying to @LaurenAnneWise @GidMK and
Whoops, I thought you meant missing indicator variable into the imputation prediction model. Is that what you meant?
1 reply 0 retweets 2 likes
Yep!
7:59 PM - 1 Aug 2019
0 replies
0 retweets
3 likes
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.