Stata running issues in MLE estimation

[Raghavendra kushawaha]

Hello everyone, I am running MLE with probabilistic data. when I am estimating the results with full data with all variables (15 variables with 134 observations) STATA is continuously running around an hour but the results are not coming. but when taking limited data from the same (around 30) it has no issue to display the results. i have continuously tried many time the same but am unable to resolve this issue.

[William Lisowski]

Your question really isn't clear without more detail, or at a minimum it is too difficult to guess at a good answer from what you have shared. Please help us help you. Show example data. Show your code. Show us what Stata told you. The Statalist FAQ provides advice on effectively posing your questions, posting data, and sharing Stata output.

[Raghavendra kushawaha]

Sir I am estimating MLE underlying the prospect theory with variables (choice, Prob1L Prob2L Prob1R Prob2R and age gender T_income Ag_income etc.). when the model estimates parameters alpha, lambda, and gamma only with model (ml model lf Raghu_MLcpt (alpha: Choices P0left P0right prize0 prize1 prize2 prize3 = ) (lambda: ) (gamma: ), vce(cluster id) nolog maximize) the results appear smoothly but including the other variables in the model i.e.
(ml model lf Raghu_MLcpt (alpha: Choices P0left P0right prize0 prize1 prize2 prize3 = Age NoF Edu NofA Chld Tincome AgT RntLT RntLG Infdebt Fdebt MSP1 MSP1 MSP2) (lambda: Age NoF Edu NofA Chld Tincome AgT RntLT RntLG Infdebt Fdebt MSP1 MSP1 MSP2) (gamma: Age NoF Edu NofA Chld Tincome AgT RntLT RntLG Infdebt Fdebt MSP1 MSP1 MSP2), vce(cluster id) nolog maximize
the result does not display and taking more than an hour of showing convergence problem. Sir, I don't think any problem in the model because estimating with limited data (30 out of 134) the outputs have displayed many times.

[Carlo Lazzaro]

Raghavendra:
as William wisely highligted, it is always difficult to advise on queries like this one without knowing data (and theory, in my case) supporting original poster's estimates.
That said, the usual recipe is to start it all over again, adding once predictor at a time and see when Stata starts gasping. Oftentimes it is a metter of a variabe with nasty values (whatever nasty might mean in this context).