py-why / py-why/EconML

invalid inference

Open
#276 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
4.8k
Forks
827
PR merge metrics
No merged PRs in 30d

Description

I'm using bootstrap inference method when I fit the dml model but I get the following error with the following command.
dml.fit(Y=y, T=t, X=x , W =w, inference='bootstrap')
Not sure what kind of co-variance matrix it can't determine but it still gives me confidence interval when I get effect interval.
~\anaconda3\lib\site-packages\econml\utilities.py:961: UserWarning: Co-variance matrix is undertermined. Inference will be invalid!
warnings.warn("Co-variance matrix is undertermined. Inference will be invalid!")

  1. Why does it give this error ?
  2. Can I trust my CI?

Contributor guide

No contributing guide indexed for this repository

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 reported dml.fit(..., inference='bootstrap') call and inspect econml/utilities.py around line 961, where the covariance warning is emitted. Reproduce the warning with the issue's inputs if available, then trace the effect interval calculation to determine whether the confidence interval is intended to remain usable when covariance is undetermined. Done means documenting the cause and whether the interval should be trusted or the behavior needs correction.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.