Sunday, February 19, 2006

st: error message with ml maximization

Hey, I wrote a little do file to estimate a simutanous equation system with switch regime and get the following error message:


initial: log likelihood = -<inf> (could not be evaluated) feasible: log likelihood = -38722.421 rescale: log likelihood = 95133.127 rescale eq: log likelihood = 230929.35 could not calculate numerical derivatives discontinuous region with missing values encountered r(430);

end of do-file r(430);


Here is my code.


capture program drop myml program myml version 8.0 args lnf theta1 theta2 lamda alpha1 beta1 beta3 sigma1 sigma2 sigma12

tempvar u1 u21 u22 r T1 T2 Badet f quietly { gen double `u1' = $ML_y1 - `theta1' - `alpha1'*lp gen double `u21' = $ML_y2 - `theta2' - `beta1'*lq gen double `u22' = $ML_y3 - `theta2' - `beta1'*lq - `beta3' gen double `r' = `sigma12'/(`sigma1'*`sigma2') gen double `T1' = ((`u1'/`sigma1')^2-2*`r'*(`u1'/`sigma1')*(`u21'/`sigma2')+(`u21'/`sigma2')^2)/(2*(1-`r'^2)) gen double `T2' = ((`u1'/`sigma1')^2-2*`r'*(`u1'/`sigma1')*(`u22'/`sigma2')+(`u22'/`sigma2')^2)/(2*(1-`r'^2)) gen double `Badet' = abs(1-`alpha1'*`beta1') gen double `f' = `Badet'*(`lamda'*exp(-`T1')+(1-`lamda')*exp(-`T2'))/(2*_pi*`sigma1'*`sigma2'*(1-`r'^2)^.5) replace `lnf' = log(`f') } end

ml model lf myml (demand: lq = lakes md*) (supply: lp = dm* md*) /lamda /alpha1 /beta1 /beta3 /sigma1 /sigma2 /sigma12 ml maximize


Could anyone give me some idea about what is going wrong? Thanks a lot!



_________________________________________________________________ Express yourself instantly with MSN Messenger! Download today it's FREE!

* * For searches and help try: * * *


Links to this post:

Create a Link

<< Home

This page is powered by Blogger. Isn't yours?