Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add metric (e.g. from regression model) to quantify the improvement of consistency #76

Closed
Tracked by #72 ...
tonyshumlh opened this issue May 20, 2024 · 2 comments · Fixed by #93
Closed
Tracked by #72 ...
Assignees
Labels
enhancement New feature or request

Comments

@tonyshumlh
Copy link
Collaborator

We can carry out F-test to test the equality of 2 variance (measurement for consistency)
We have 2 samples (1. before prompt/checklist/code change, 2. after prompt/checklist/code change)
Null Hypothesis: Sigma_1^2 = Sigma_2^2
Alternative Hypothesis: Sigma_1^2 > Sigma_2^2 (we want to prove if new change is more consistent than the original setting)
https://www.itl.nist.gov/div898/handbook/eda/section3/eda359.htm

@JohnShiuMK
Copy link
Collaborator

According to #72 and #99
I will update the consistency F-test from one-tail to two-tail (keep it in jupyter notebook)

  • (optional) to look at stat package if have time

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants