Dear Stephane,
it is not clear why the estimate of sig is very suspicious, 0.98783 is not much different from 1.
You can find below the new output.
converged
Additional convergence test using scaled estimation. Parameters will be scaled by their current estimates and additional iterations will
be performed.
initial value 2202686.525949
iter 1 value 2202686.525849
final value 2202686.525849
converged
Estimated parameters with approximate standard errors from BHHH matrix:
Estimate BHHH se BHH t-ratio (0)
alpha_base -1.25928 0.001142 -1103.036
gamma_CERE 2.77770 0.006557 423.618
gamma_CONF 1.74657 0.004230 412.874
gamma_DAIR 2.83847 0.007012 404.787
gamma_DRIN 17.26285 0.035960 480.061
gamma_FRUI 3.24903 0.007478 434.475
gamma_MEAT 1.07479 0.002716 395.709
gamma_FISH 1.62149 0.005695 284.710
gamma_OTHE 1.40383 0.003324 422.284
deltamu_CERE -0.04007 0.006318 -6.342
deltamu_CONF 0.75572 0.006352 118.964
deltamu_DAIR 0.72941 0.006612 110.313
deltamu_DRIN -2.69537 0.007025 -383.709
deltamu_FRUI -0.50316 0.006327 -79.531
deltamu_MEAT -0.01909 0.007139 -2.674
deltamu_FISH -0.76338 0.007611 -100.302
deltamu_OTHE 0.00000 NA NA
deltasigma_CERE -0.35498 0.001410 -251.685
deltasigma_CONF -0.53306 0.001486 -358.653
deltasigma_DAIR 0.52056 0.001358 383.407
deltasigma_DRIN 0.79998 0.001788 447.374
deltasigma_FRUI -0.77482 0.001667 -464.809
deltasigma_MEAT 0.85508 0.002032 420.733
deltasigma_FISH -0.51846 0.001904 -272.349
deltasigma_OTHE 0.00000 NA NA
bq1_CERE -0.02788 0.008530 -3.268
bq1_CONF -0.12072 0.008580 -14.071
bq1_DAIR -0.02252 0.008791 -2.562
bq1_DRIN 0.02902 0.009672 3.001
bq1_FRUI 0.12215 0.008502 14.366
bq1_MEAT -0.07806 0.009779 -7.983
bq1_FISH -0.06512 0.010687 -6.094
bq2_CERE -0.05012 0.008572 -5.848
bq2_CONF 0.03191 0.008585 3.716
bq2_DAIR 0.06663 0.008830 7.545
bq2_DRIN 0.32297 0.009533 33.879
bq2_FRUI 0.25215 0.008344 30.218
bq2_MEAT 0.07271 0.009803 7.417
bq2_FISH 0.13363 0.010447 12.791
bq3_CERE -0.03539 0.008864 -3.993
bq3_CONF 0.06419 0.008828 7.271
bq3_DAIR 0.11972 0.009151 13.082
bq3_DRIN 0.53834 0.009782 55.034
bq3_FRUI 0.08647 0.008945 9.667
bq3_MEAT 0.18953 0.010372 18.274
bq3_FISH 0.31659 0.011038 28.682
bq1_OTHE 0.00000 NA NA
bq2_OTHE 0.00000 NA NA
bq3_OTHE 0.00000 NA NA
sig 1.00000 NA NA
Final LL: -2202686.5258
Important: Read this before posting to this forum
- This forum is for questions related to the use of Apollo. We will answer some general choice modelling questions too, where appropriate, and time permitting. We cannot answer questions about how to estimate choice models with other software packages.
- There is a very detailed manual for Apollo available at http://www.ApolloChoiceModelling.com/manual.html. This contains detailed descriptions of the various Apollo functions, and numerous examples are available at http://www.ApolloChoiceModelling.com/examples.html. In addition, help files are available for all functions, using e.g. ?apollo_mnl
- Before asking a question on the forum, users are kindly requested to follow these steps:
- Check that the same issue has not already been addressed in the forum - there is a search tool.
- Ensure that the correct syntax has been used. For any function, detailed instructions are available directly in Apollo, e.g. by using ?apollo_mnl for apollo_mnl
- Check the frequently asked questions section on the Apollo website, which discusses some common issues/failures. Please see http://www.apollochoicemodelling.com/faq.html
- Make sure that R is using the latest official release of Apollo.
- Users can check which version they are running by entering packageVersion("apollo").
- Then check what is the latest full release (not development version) at http://www.ApolloChoiceModelling.com/code.html.
- To update to the latest official version, just enter install.packages("apollo"). To update to a development version, download the appropriate binary file from http://www.ApolloChoiceModelling.com/code.html, and install the package from file
- If the above steps do not resolve the issue, then users should follow these steps when posting a question:
- provide full details on the issue, including the entire code and output, including any error messages
- posts will not immediately appear on the forum, but will be checked by a moderator first. This may take a day or two at busy times. There is no need to submit the post multiple times.
Function evaluation limit exceeded.
-
stephanehess
- Site Admin
- Posts: 1142
- Joined: 24 Apr 2020, 16:29
Re: Function evaluation limit exceeded.
ah, sorry, I got confused by the formatting and was looking at the wrong column.
It's still not exactly clear what is going wrong with your model. My only suggestion is to gradually add the random terms, not all at once
It's still not exactly clear what is going wrong with your model. My only suggestion is to gradually add the random terms, not all at once
Re: Function evaluation limit exceeded.
Dear Stephane,
I actually get satisfactory results with the BFGS estimation method, so the problem is related to bgw estimation algorithm.
For the time being, I think I will not dig into it and take the results from BFGS for my research project.
Thanks for your help.
Beatrice Biondi
I actually get satisfactory results with the BFGS estimation method, so the problem is related to bgw estimation algorithm.
For the time being, I think I will not dig into it and take the results from BFGS for my research project.
Thanks for your help.
Beatrice Biondi
-
stephanehess
- Site Admin
- Posts: 1142
- Joined: 24 Apr 2020, 16:29
Re: Function evaluation limit exceeded.
BGW is more reliable/stable than BFGS and we have seen many cases where BFGS fails to identify issues with the model. So one thing you should definitely do is use the BFGS results as starting values with BGW to see whether your model is actually identified