This package provides a collection of methods for doing SFA (Stochastic frontier analysis) based on traditional statistical techniques.
Its development was inspired by some existing software for SFA (R packages frontier, sfa and Benchmarking, Stata commands frontier
, xtfrontier
and sfcross
/sfpanel
).
This package is in beta version. It is mostly functional but the interface and some features are still under development. Therefore it is not ready for regular use yet.
Contributions and suggestions are welcome!
The package is not on CRAN yet. Install it from its GitHub repo.
library(devtools)
install_github("vh-d/SFAt")
cross-section models - distributions: - normal/half-normal - normal/truncated normal - normal/exponential - homoskedasticity and heteroskedasticity for both symmetric and inefficiency terms - conditional mean (BC, 1995) model
panel data models - panel data conditional mean (BC, 1995) model can be estimated via cross-section model specification - CSS, 1990 model
optimx
package for MLE optimization Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.