Skip to content

Covariate adjustment for continuous and binary trait #1209

Description

@pupatel

I am trying to use ResAdjTranformer() for feature-only adjustments. How do I adjust for a continuous and binary trait together?

Context of the issue

I have done the adjustment by individual covariates depending on their type. For example, I used linear regression to adjust Age, and for binary trait-like Sex use logistic regression.

Here's the sample covariate file:
Feature, Type , Covariates
Feature-1 , linear , Age
Feature-1 , logistic , Sex
Feature-2 , linear , Age
Feature-2 , logistic , Sex
...

Could I do the following and TPOT will take of the binary trait automatically?
Feature-1, linear, Age;Sex

Additionally, after I use ResAdjTranformer(), Is there a way to know % variance explained by each covariate across different features? If so, could you please guide me to an example?

Thank you so much for helping me in advance.

Best,
P.

Activity

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

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions