I think Quillette should have a widget that covers the Daily Lehman-Taleb Twitter Fight
-
-
Replying to @anarchomorphist @clairlemon
Fucking moron it's not a fight: it's watching her do self-flagellation, which gets painful once it starts eliciting commiseration.
27 replies 13 retweets 173 likes -
Claire is not pushing a "human biodiversity" agenda, but even if she thought, empirically, that there were average differences between populations, that would not make her a "neonazi." Why are you throwing around labels so carelessly?
1 reply 0 retweets 5 likes -
Replying to @LevelOAnalysis @nntaleb and
Who cares, the important thing is she was baited into responding and in going so removing any remaining shred of doubt that she's an utter IYI. "They can’t tell science from scientism — in fact in their image-oriented minds scientism looks more scientific than real science."
1 reply 0 retweets 1 like -
Replying to @TrevorSutcliffe @nntaleb and
Taleb comes across much worse in the exchange. I don't what you are talking about.
1 reply 0 retweets 3 likes -
Replying to @LevelOAnalysis @nntaleb and
Trevor Sutcliffe Retweeted Claire Lehmann
Ah yes, she was in really fine form when she argued that you can't dispute the way social scientists make unsound assumptions and employ statistical techniques copped from probability theory by making mathematical arguments based in probability theory.https://twitter.com/clairlemon/status/1156034873934508035?s=20 …
Trevor Sutcliffe added,
Claire LehmannVerified account @clairlemonYou can't debunk the predictive utility of a diagnostic test with mathematical theory. The test is either predictive real world outcomes or it is not. In the rush to be a philosophers of science some people forget to be actual scientists. https://twitter.com/Monsantobuster/status/1156027566349664258?s=20 …2 replies 0 retweets 6 likes -
Replying to @TrevorSutcliffe @nntaleb and
That's not what she's saying. She's saying certain correlations are mere matters of fact not the sorts of things that can be refuted with mathematical legerdemain. If rain correlates with the ground being wet, this is a mere matter of fact. Not the sort of thing math can refute.
3 replies 0 retweets 1 like -
Replying to @LevelOAnalysis @nntaleb and
A linear correlation coefficient is only suitable when there are linear relationships between variables. Taleb's point is that the relationship between IQ and income/performance is nonlinear at higher levels of IQ. That's not "legerdemain".
1 reply 0 retweets 0 likes -
Replying to @TrevorSutcliffe @nntaleb and
Taleb happens to be wrong about that. Lubinski and Benbow have shown in prospective studies with a large sample that IQ is still predictive at the very highest levels, and keeps working at each higher band.
1 reply 0 retweets 0 likes -
Replying to @LevelOAnalysis @nntaleb and
You don't understand correlation. Being able to "show" a linear relationship by applying a linear regression when the relationship between variables is in fact nonlinear leads to errors in reasoning. If you don't understand the math, you're clueless. Common in social sciences.
1 reply 0 retweets 1 like
What is your evidence that the relationship between IQ and income/performance is nonlinear at higher levels of IQ.
-
-
Replying to @LevelOAnalysis @nntaleb and
Not my evidence. Here is Taleb's article. Note: even if the relationship were entirely linear and the data wasn't so noisy, Claire's claim that you can't make an argument about the predictive utility of something by using math would be absurd on its face.https://medium.com/incerto/iq-is-largely-a-pseudoscientific-swindle-f131c101ba39 …
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.