MNL Tests #132
Merged
MNL Tests #132
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
I think it'd be worthwhile to add some documentation about the inputs and assumptions in the mnl code, I'll add that Monday. |
|
Good call (on the documentation) - let me know if I can help |
|
@fscottfoti Have a quick look at e13f5cd and make sure my docstrings make sense, then this is ready (I think). |
jiffyclub
added a commit
that referenced
this pull request
Nov 24, 2014
Tests comparing mnl code to R's mlogit
jiffyclub
added a commit
to ActivitySim/activitysim
that referenced
this pull request
Mar 13, 2015
The data was in turn copied from R. For more info on the UrbanSim mnl tests refer to these PRs: UDST/urbansim#132 UDST/urbansim#135
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I generated test data and results using R's mlogit package and used those to validate the numbers from our MNL package for both estimation (comparing coefficients) and simulation (comparing probabilities). The only change I had to make to mnl.py to get a good match (to one part in 10000) was to lower the threshold that terminates the SciPy optimization.