Hi all,
I recently estimated a mode choice model based on RP and SP data. Some alternatives are only available in the SP data and hence, there are parameters (e.g., travel time parameters for these modes) which are only estimated based on the SP data. The mu of the SP data is around 0.5, whereas the mu of the RP data is fixed to 1. However, it seems to me that the estimates of the parameters which are only estimated based on the SP data are not scaled in the results file, since the VoT for those modes are around 1/mu as high as for modes for which the parameters are estimated on both RP and SP data.
So, can the parameters be used as they are shown in the estimates file or have the be multiplied with mu before using them in a prediction model?
Thanks!
Best,
Michael
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.
Joint RP/SP estimation: interpretation of mu and estimates
-
mastermoses
- Posts: 5
- Joined: 04 Dec 2020, 07:34
-
stephanehess
- Site Admin
- Posts: 998
- Joined: 24 Apr 2020, 16:29
Re: Joint RP/SP estimation: interpretation of mu and estimates
Michael
if you set mu=1 for RP, then all the betas are at the RP scale, even if they are only used in the SP utilities, as long as the entire utility function is multiplied by mu.
Can you share your utility files and results?
Stephane
if you set mu=1 for RP, then all the betas are at the RP scale, even if they are only used in the SP utilities, as long as the entire utility function is multiplied by mu.
Can you share your utility files and results?
Stephane
-
mastermoses
- Posts: 5
- Joined: 04 Dec 2020, 07:34
Re: Joint RP/SP estimation: interpretation of mu and estimates
Hi Stephane,
unfortunately I cannot share any file since this work is confidential and not published yet. However, I use seperate models or each data source and combine them with apollo_combineModels. For the mu, I have
applied to the cnl_settings of each model and of course the mu_rp set to 1.
So does that mean that for prediction, the parameters can be used as estimated in the final mode choice model?
Best
Michael
unfortunately I cannot share any file since this work is confidential and not published yet. However, I use seperate models or each data source and combine them with apollo_combineModels. For the mu, I have
Code: Select all
cnl_settings$V = lapply(V, "*", mu_*) % where the mu_* stands for the mu of each data set So does that mean that for prediction, the parameters can be used as estimated in the final mode choice model?
Best
Michael
-
stephanehess
- Site Admin
- Posts: 998
- Joined: 24 Apr 2020, 16:29
Re: Joint RP/SP estimation: interpretation of mu and estimates
Michael
yes, but in prediction, you of course need to decide which scale to use. The natural approach would be to use the RP scale
Stephane
yes, but in prediction, you of course need to decide which scale to use. The natural approach would be to use the RP scale
Stephane
-
mastermoses
- Posts: 5
- Joined: 04 Dec 2020, 07:34
Re: Joint RP/SP estimation: interpretation of mu and estimates
Hi Stephane,
thank you for the quick reply. As I understood it, it is not common to use different scales for different alternatives in prediction, right?
Best
Michael
thank you for the quick reply. As I understood it, it is not common to use different scales for different alternatives in prediction, right?
Best
Michael
-
stephanehess
- Site Admin
- Posts: 998
- Joined: 24 Apr 2020, 16:29
Re: Joint RP/SP estimation: interpretation of mu and estimates
no, that wouldn't make much sense