I am new to MLE programming and have never done it on Stata before. I am estimating a stochastic production function following Just-Pope (1978).

The formula is the following:

enter image description here

I understand in theory that Stata will maximize the log likelihood function through an iterative method, using the FGLS estimates of the parameters to start. I am, however unable to translate this into code. Previously, I estimated this production function using FGLS, and coded it using loops, but now I'm not sure how I can do this and if I can include fixed effects for instance.

I tried something of the form:

program define maxlike

version 14.0 

args lnf xb xdelta 

quietly replace `lnf' = -.5*[_N * ln(2*_pi) + ($ML_y1 - (`xbeta')^2/exp(`xdelta')) + `xdelta']

ml model lf normal (mean:  yield_pl*=) (var:  yield_pl*=)


But of course it's not working. Any pointers or references on how I can do this would be greatly appreciated. I should mention that I am working with panel data.

Thank you very much in advance!


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.