Forum: help
Monitor Forum | 
Start New Thread
| RE: sfa problem: "Error in optim - non-finite value supplied by optim" [ Reply ] By: Giota Siameti on 2021-03-09 16:47 | [forum:48795] |
|
Hi, Did you find a solution to the error you reported regarding Frontier? I am currently using sfa and I encounter the same problem. I would appreciate your help since I need to analyze some data for my PHD. Thanks in advance, Siameti Giota |
|
| RE: sfa problem: "Error in optim - non-finite value supplied by optim" [ Reply ] By: Vinzenz Peters on 2020-05-12 13:25 | [forum:47770] |
|
Hey Kathi, were you able to solve this problem? If yes, I'd be curious to hear how as I am currently facing similar difficulties... |
|
| sfa problem: "Error in optim - non-finite value supplied by optim" [ Reply ] By: Kathi Neuman on 2020-02-13 11:06 | [forum:47389] |
|
Hi, I am trying to use the frontier package in R, however, when I run the code I receive the error message: "Error in optim(pars, fn = maxlik, y = y, X = X, sc = sc, hessian = TRUE, : non-finite value supplied by optim" Googeling around, I tried to switch the optimisation method, but I get the same error for all of these methods: “Nelder-Mead”, “BFGS”, “CG”, “L-BFGS-B”, “SANN”, “Brent” I double checked if the variables are numeric, which they are. I tried to run the same dataset in the front.41 software package (so not in R), which worked fine. I want to use R rather than the frontier software to obtain the fitted values and to have a code that could be replicated. Does anyone have an idea what could be the issue here? Thank you! Kathi |
|
