Hi
I am trying to do a route choice model. The data is not surveyed data but synthesized. The routes were generated based on directness measure assuming a unit demand. There were a total of 22 routes generated and the generated data were then grouped into 10 alternatives based on the normalized cdf of the excess directness measure and path size. The MNL was run on the groups assuming 22 individual and the choice being 1 to 10. However the results are not good. Since I didn't know what should be the path size for non chosen alternative (given that each of the 10 alternatives have the following proportions) I did the mnl on excess directness measure only.
Final identified cluster number Probability
1 0.181818
2 0.090909
3 0.272727
4 0.136364
5 0.045455
6 0.045455
7 0.045455
8 0.045455
9 0.045455
10 0.090909
the result was as follows:
Model name : MNL5847_final_paper
Model description : Simple MNL model on mode choice SP data
Model run at : 2025-07-29 16:48:08.974224
Estimation method : bgw
Model diagnosis : Relative function convergence
Optimisation diagnosis : Maximum found
hessian properties : Negative definite
maximum eigenvalue : -2.203768
reciprocal of condition number : 1
Number of individuals : 22
Number of rows in database : 22
Number of modelled outcomes : 22
Number of cores used : 1
Model without mixing
LL(start) : -50.66
LL at equal shares, LL(0) : -50.66
LL at observed shares, LL(C) : -45.64
LL(final) : -50.06
Rho-squared vs equal shares : 0.0117
Adj.Rho-squared vs equal shares : -0.008
Rho-squared vs observed shares : -0.0969
Adj.Rho-squared vs observed shares : 0.0783
AIC : 102.13
BIC : 103.22
Estimated parameters : 1
Time taken (hh:mm:ss) : 00:00:0.25
pre-estimation : 00:00:0.19
estimation : 00:00:0.03
post-estimation : 00:00:0.03
Iterations : 4
Unconstrained optimisation.
Estimates:
Estimate s.e. t.rat.(0) Rob.s.e. Rob.t.rat.(0)
asc_route1 0.0000 NA NA NA NA
d -0.7274 0.6736 -1.080 0.6498 -1.119
the rho -square values are negative. what should/can i do to improve them.
regards
Padma
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.
negative rho values
-
stephanehess
- Site Admin
- Posts: 1351
- Joined: 24 Apr 2020, 16:29
Re: negative rho values
Hi
essentially, your model is nearly random, the LL does not really improve over the LL0. Maybe your data simulation itself is too random or maybe too deterministic
Stephane
essentially, your model is nearly random, the LL does not really improve over the LL0. Maybe your data simulation itself is too random or maybe too deterministic
Stephane