Stata is certainly capable of this, as documented in the manual : frontier can fit models in which the nonnegative distribution component (a measurement of inefficiency) is assumed to be from a half-normal, exponential, or truncated-normal distribution. Have a look at the manual here :
https://www.stata.com/manuals/rfrontier.pdf
Without more detail of your problem that's as much as I can say.
Perhaps I'm just overly curious, but I always wonder why people post questions like, "How can I do X with {some stats package}?" to RG when there is a perfectly good discussion forum for that stats package. In other words, have you considered posting your question to Statalist?
If you do post there, please read the FAQ first, as it has some excellent advice on how to craft your question in a way that makes it more answerable.
- https://www.statalist.org/forums/forum/general-stata-discussion/general
- https://www.statalist.org/forums/help
PS- Pay attention the FAQ item on Stata vs STATA. Some of the regulars get a bit grumpy when people use the latter. ;-)
Joshy Mathew K, the private message you sent me shows that you are using -sfpanel-, which is a user-written package. The -frontier- command that Ronán Michael Conroy referred to is an official Stata command. I suggest that you try using it.
- https://www.stata.com/manuals/rfrontier.pdf
PS- I have no experience with this command, but I see that the word inefficiency appears 31 times in the help file. So if you have further questions, I repeat my suggestion that you post to Statalist.
- Badges
- Science topic
- Similar topics
- Engineering
- Computer Engineering
- Computer