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.

Sign up for GitHub

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

Jump to bottom

organise_phenotypes - outlier detection and removal #4

Open

explodecomputer opened this issue Aug 10, 2023 · 1 comment

Assignees

Contributor

explodecomputer commented Aug 10, 2023

No description provided.

explodecomputer linked a pull request

that will close this issue

added a random line #5

Closed

eleanorsanderson self-assigned this

Contributor Author

explodecomputer commented Nov 10, 2023 •

edited

Loading

Use phen definitions to remove outliers due to measurement error
Use windsorising to reduce influencers - GoDMC implements quartile +/- 3xIQR to detect outliers and windsorises them to re-value them at 5/95% value.

Update

This won't work with a cohort with multiple ages

Remove outliers based on definition
y ~ age + age^2 - get residuals
Windsorise residuals
Reconstruct phenotype as y_new = age * b1 + age^2 * b2 + new_residuals + intercept

Assumes constant variance with age - does using age quadratic hinder?

Good to try simulating

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment