Work in progress. Data is VES, n≈4400. https://www.cdc.gov/nceh/veterans/default1c.htm … We will be releasing this as an open dataset for all. :) @Kane_WMC_Lab
-
-
Replying to @KirkegaardEmil
I was lazy and only used AFQT for this, but will use g factor from ~20 tests later. http://rpubs.com/EmilOWK/VES_dataset_paper …
@Kane_WMC_Lab1 reply 0 retweets 1 like -
Replying to @KirkegaardEmil @Kane_WMC_Lab
Maybe unreliable pupil var? What's your regression of pupil size on IQ? 1 SD in IQ -> .45 mm in earlier study.
1 reply 0 retweets 0 likes -
Replying to @pnin1957
Read the link and you will see that left eye x right eye is r = .97.
@pnin1957@Kane_WMC_Lab1 reply 0 retweets 0 likes -
Replying to @KirkegaardEmil @Kane_WMC_Lab
That seems like a strong indication of unreliability, given how common anisocoria is: https://en.wikipedia.org/wiki/Anisocoria
1 reply 0 retweets 0 likes -
The unstandardized regression slope would be interesting as measurement error in DV doesn't bias it.
1 reply 0 retweets 0 likes -
Replying to @pnin1957
I guess you can examine that when the data comes out. :) It is only intended to showcase the dataset.
@pnin1957@Kane_WMC_Lab1 reply 0 retweets 0 likes -
Replying to @KirkegaardEmil @Kane_WMC_Lab
Okay :) My prediction is that much of the discrepancy b/w your and earlier results may be due to unreliability
1 reply 0 retweets 0 likes -
Replying to @pnin1957
Your suggestion fails the reversal test. http://andrewgelman.com/2016/01/26/more-power-posing/ …
@pnin1957@Kane_WMC_Lab1 reply 0 retweets 0 likes -
Replying to @KirkegaardEmil @Kane_WMC_Lab
Not really. Tsukahara's precision seems to be .1 mm, you seem to have 1 mm. Should cause some diffs in corrs.
1 reply 0 retweets 0 likes
Very slight. Why don't you just simulate data and see? Don't be so lazy. @pnin1957 @Kane_WMC_Lab
-
-
Replying to @KirkegaardEmil @Kane_WMC_Lab
Nah, that sounds like work. Tsukahara had 95% CI .25-.45, so I'd be surprised if there are no moderators.
0 replies 0 retweets 0 likesThanks. 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.