Thanks. Estimation of the same model with the same dataset gives different results when "tsls" (from package sem) is used as opposed to "ivreg()" (from package AER); both parameter estimates and standard errors are different. This is intriguing. Can anyone throw some light on this? Is there any reason to prefer one to the other?
Deepankar On Sun, May 2, 2010 at 3:51 PM, Achim Zeileis <achim.zeil...@uibk.ac.at>wrote: > On Sun, 2 May 2010, Dipankar Basu wrote: > > Hi All, >> >> I am using R 2.11.0 on a Ubuntu machine. I estimated a model using "tsls" >> from the package "sem". Is there a way to get Newey West standard errors >> for >> the parameter estimates? >> >> When estimating the model by OLS, I used "NeweyWest" from the package >> "sandwich" to get HAC standard errors. But, I am not able to use the same >> method with the results of the "tsls" estimation. >> > > You can use ivreg() from package "AER" which provides a few more methods > than tsls(). In particular, it provides an estfun() method so that the > covariance matrix estimators from "sandwich" can be employed. > Z > > Any help would be appreciated. >> >> Deepankar >> >> [[alternative HTML version deleted]] >> >> ______________________________________________ >> R-help@r-project.org mailing list >> https://stat.ethz.ch/mailman/listinfo/r-help >> PLEASE do read the posting guide >> http://www.R-project.org/posting-guide.html >> and provide commented, minimal, self-contained, reproducible code. >> >> [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
