11.12 Packages & Functions: wfe & PanelMatch
- Ideally, now use wfe package and the
wfe()
function (K. Imai and Kim 2019b) or thePanelMatch
package and the corresponding functionPanelMatch()
wfe()
: Fitting the Weighted Fixed Effects Model for Causal Inferenceunit.index =
andtime.index =
: Specify the index variables (unit’s id and time)method =
:unit
for unit,time
for time fixed effectsqoi =
: Quantity of interest45estimator =
: DefaultNULL
(should be fe); One offd
,did
, orMdid
- For the rest see
?wfe
- The just published
PanelMatch
package looks extremely promising and will likely replace earlier packages such asplm
orwfe
(see announcement)- Currently, the lab sessions are a mixture of these packages
References
Imai, Kosuke, and In Song Kim. 2019b. “When Should We Use Unit Fixed Effects Regression Models for Causal Inference with Longitudinal Data?” Am. J. Pol. Sci. 63 (2): 467–90.
One of
ate
oratt
. The default isate
. If set toatt
in implementingfd
anddid
estimators, the comparison of the treated observation is restricted to the control observation from the previous time period but not with the control observation from the next time period.↩