Open mleipzig opened 3 years ago
The error from SuperLearner says "Currently only works with gaussian data". This means you cannot use SL.ridge with a binary treatment; it can only be used with a continuous treatment. I'll look into making the WeightIt warnings better in this scenario and see if I can make it fail more gracefully.
I tried to use SuperLearner with WeightIt using this code and everything worked just fine with Sl.glm, but ridge led to some errors.
W.out <- weightit(treat ~ age + educ + race + married + nodegree + re74 + re75, data = lalonde, estimand = "ATE", method = "super", SL.method = "method.balance", SL.library = c("SL.glm", "SL.ridge" ))
and got this