statsmodels / statsmodels/statsmodels

ENH: API for outlier_test in OLSResults

Open
#2,328 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

comp-regression comp-stats type-enh
Dominant language
Python
Stars
11.6k
Forks
3.6k
Avg merge
7h 37m
Merged PRs (30d)
96

Description

I'm running the outlier test with plain numpy arrays as data, and the return of outlier_test is just an array with 3 columns. This should be made more convenient and informative, maybe return a results class, and an option to show only the top results.
(some of this is redundant if pandas has been used for the model data)

Also, the function in outlier_influence has labels and order options but those are not available in the OLSResults method.

(there should be related issues for extending outlier_test to other models.)

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the OLSResults outlier_test method and compare it with the function in outlier_influence, especially their existing labels and order options. Clarify the desired results-class and top-results behavior, then verify that the OLSResults API supports informative output for NumPy-array data while retaining the existing three-column results.

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
Mostly clear
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.