Perhaps he was "thinking this as he read it" because I actually use the fitness analogy at some point myself!
-
...in the data, explains a lot of the variance (again, could've been otherwise), and predicts stuff IRL.
*nod* but if those are the only criteria, we'd end up granting existence to nonsense variables ...
-
-
...like "IQ plus cube root of height" if they turned out to correlate w irl stuff (as that one likely would)
-
and i think the "not a nonsense variable" criterion is hiding some casual theorizing on our part
-
correlation between a "nonsense var" and (say) income would be uninteresting bc we'd know it wasn't causal
-
so when we grant "existence" we're saying "this seems like a good candidate for a node in a causal model"
-
if we go from pure descriptive stats to "this exists," we've smuggled in some causal claims under the radar
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.