I would say this is flogging a dead horse, but perhaps the horse is alive and kicking in non-econ fields? Polynomial regression performs poorly at endpoints. Everybody I know knows this. The package every economist now uses (rdrobust) uses a local polynomial for this very reason.
Chaser: Why High-Order Polynomials Should Not Be Used in Regression Discontinuity Designs http://www.stat.columbia.edu/~gelman/research/published/2018_gelman_jbes.pdf …https://twitter.com/yarbsalocin/status/1193972022109462529 …
-
-
-
I avoid all these problems by simply using a 1,000-degree polynomial for all my regressions
End of conversation
New conversation -
-
-
Also great title!
@SayWhatYouFoundThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Ah, this explains my confusion here, I think.https://twitter.com/yarbsalocin/status/1193982449698639877 …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Hm. This looks like an output from the Cattaneo et al. rdrobust procedure...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This is fractally bad. I keep finding new things. What is going on with bin size on the right hand side of the cut off?!?!?
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.