statsmodels / statsmodels/statsmodels
diagnostic tests: results instance with intermediate results
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.6k
- Forks
- 3.6k
- Avg merge
- 7h 37m
- Merged PRs (30d)
- 96
Description
In cases where some tests like het_breushpagan rejects the Null of no heteroscedasticity it would be interesting to look at which auxiliary variables are significant in the artificial direction.
This would help in getting an idea in which "alternative direction" the Null is rejected.
In this case, what would be likely candidates for including in estimating a variance function.
(not only for linear_model, I looked at a case with heteroscedasticity after estimating a Poisson model)
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the het_breushpagan diagnostic and the result objects used by linear_model and Poisson models. Define which intermediate auxiliary-variable results should be exposed and how callers would identify significant variables or alternative directions; no specific files or tests are named in the issue.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- analytics, data
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100