You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In a comment on the -reghdfe- branch, I've just submitted a test script which demonstrates that -margins- works fine after -reghdfe- when there are no instrumental variables.
This test script testivreghdfe.zip
shows that, after estimation of a fixed-effects IV model with -reghdfe,old-, -margins- does work with the -contrasts- option or with the -dydx- option. However, -margins does not work in the absence of those options.
The test script compares the performance of -reghdfe, old- to the performance of Stata's official --ivregress- and -xtivreg,fe- commands. the comparison suggests that -ivreghdfe- could be compatible with -margins- if its treatment of the constant term were more similar to the treatment accorded the constant by Stata's -xtivreg,fe- command.
Code:
sysuse auto, clear reghdfe price weight i.foreign (length=gear), absorb(turn trunk) old margins i.foreign
Underlying issue: ivreg2 does not support margins if used with partial()
Possible soln: study when is it valid to use margins+partial
The text was updated successfully, but these errors were encountered: