Hi
they are clearly not the same model. You need to get exactly the same results for MNL. Can you show us the specification for both packages? I note the Stata one has a constant for example
Regarding item_4, this will work, but you need to include it in the utility functions of course
Stephane
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. We check the forum at least twice a week. It may thus take a couple of days for your post to appear and before we reply. There is no need to submit the post multiple times.
Search found 1344 matches
- 23 Jan 2026, 12:27
- Forum: Estimation results
- Topic: Mixed Logit Model for BWS: differences between Apollo and Stata estimations + baseline option issue in Apollo
- Replies: 3
- Views: 122
- 22 Jan 2026, 07:46
- Forum: Estimation results
- Topic: Mixed Logit Model for BWS: differences between Apollo and Stata estimations + baseline option issue in Apollo
- Replies: 3
- Views: 122
Re: Mixed Logit Model for BWS: differences between Apollo and Stata estimations + baseline option issue in Apollo
Hi
as a first step, can you confirm that you get exactly the same results with MNL in both packages?
Stephane
as a first step, can you confirm that you get exactly the same results with MNL in both packages?
Stephane
- 22 Jan 2026, 07:45
- Forum: Estimation results
- Topic: Unexpected sign for remuneration coefficient
- Replies: 1
- Views: 56
Re: Unexpected sign for remuneration coefficient
Hi
this could well have to do with your first alternative, which I assume is an opt-out? What were the levels for that?
Stephane
this could well have to do with your first alternative, which I assume is an opt-out? What were the levels for that?
Stephane
- 28 Dec 2025, 14:51
- Forum: Bug reports
- Topic: Element gradientObs not in model object
- Replies: 3
- Views: 1101
Re: Element gradientObs not in model object
sorry, not at present. It should be possible in a month or so
- 17 Dec 2025, 13:36
- Forum: Bug reports
- Topic: Element gradientObs not in model object
- Replies: 3
- Views: 1101
Re: Element gradientObs not in model object
hi
this was in an earlier version of Apollo, and is not currently implemented. It will be added again in the near future, but requires a change to the bgw optimiser first
Stephane
this was in an earlier version of Apollo, and is not currently implemented. It will be added again in the near future, but requires a change to the bgw optimiser first
Stephane
- 15 Dec 2025, 10:46
- Forum: Estimation results
- Topic: Difference between standard vs robust t-ratios
- Replies: 1
- Views: 723
Re: Difference between standard vs robust t-ratios
Hi
yes, these differences are very large, and also go in the opposite direction of what we typically see. Did you try a basic version of the model, without all the attributes?
Stephane
yes, these differences are very large, and also go in the opposite direction of what we typically see. Did you try a basic version of the model, without all the attributes?
Stephane
- 29 Nov 2025, 13:41
- Forum: Installation and updating
- Topic: Error in value[[3L]](cond) : unused argument (cond) in in Hybrid MMNL Model
- Replies: 1
- Views: 1022
Re: Error in value[[3L]](cond) : unused argument (cond) in in Hybrid MMNL Model
Hi
apologies for the slow reply. Could you share your code and data with me outside the forum and I'll have a look for you
Stephane
apologies for the slow reply. Could you share your code and data with me outside the forum and I'll have a look for you
Stephane
- 29 Nov 2025, 13:38
- Forum: Model specification
- Topic: Doubts about model specification with an alternative vs. status quo
- Replies: 5
- Views: 1612
Re: Doubts about model specification with an alternative vs. status quo
hi
what I mean is that you could estimate a parameter for each level, and then plot their estimates against the values and see if it looks linear
Stephane
what I mean is that you could estimate a parameter for each level, and then plot their estimates against the values and see if it looks linear
Stephane
- 29 Nov 2025, 13:36
- Forum: Model estimation
- Topic: Latent Class Choice Model: NaNs produced
- Replies: 1
- Views: 1051
Re: Latent Class Choice Model: NaNs produced
Hi
in general, using LVs in the class allocation model is empirically difficult and often leads to issues.
In your case, I would look at those parameters for which you do not obtain classical standard errors
Stephane
in general, using LVs in the class allocation model is empirically difficult and often leads to issues.
In your case, I would look at those parameters for which you do not obtain classical standard errors
Stephane
- 29 Nov 2025, 13:33
- Forum: Model specification
- Topic: weighted choice model
- Replies: 1
- Views: 806
Re: weighted choice model
Hi
no, it cannot. The weights need to be provided by the user as values
Stephane
no, it cannot. The weights need to be provided by the user as values
Stephane