Yup. But there were fewer Asians back when they started these programs esp. SMPY. You used the current value. :)
-
-
Replying to @KirkegaardEmil @JamesPsychol
Sure. Underestimates Asian, overestimates Caucasian. But I don't know what the SMPY/TIP-era values should be.
1 reply 0 retweets 0 likes -
Replying to @gwern @JamesPsychol
Also TIP is North Carolina only, so use Asian for that state%. https://en.wikipedia.org/wiki/Demography_of_the_United_States#Race_and_ethnicity … boosts Asian more, I'd think.
1 reply 0 retweets 0 likes -
Replying to @KirkegaardEmil @gwern
I used 1970 national values. May have been wrong, but looked best match with birth dates
1 reply 0 retweets 0 likes -
Replying to @JamesPsychol @KirkegaardEmil
Using 0.77 white/0.007 Asian, I now get 99.8/111.9. Seems high: http://pastebin.com/cQRek6Rm plus an ABC inference.
1 reply 0 retweets 1 like -
Replying to @gwern @KirkegaardEmil
Yes, method of limits has a high error term, I think, altho very informative if no good pop IQ measures
2 replies 0 retweets 0 likes -
Replying to @JamesPsychol @KirkegaardEmil
That might be it. We'll see what sort of 95% credible interval my ABC analysis spits out when it finishes.
1 reply 0 retweets 0 likes -
-
Replying to @JamesPsychol @KirkegaardEmil
Yes, wide CIs: 91-98 for white, 103-114 for Asians. https://i.imgur.com/AEQuZy0.png Well, that was fun.
1 reply 0 retweets 0 likes -
1 reply 0 retweets 1 like
I guess I could make a visualization about this. :)
-
-
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.