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

Explore adding multivariable analyse_pars() and pool_pars() functions #330

Open
wolbersm opened this issue Mar 10, 2022 · 1 comment
Open
Assignees
Labels
To be evaluated issues that must be discussed whether/how they have to be implemented

Comments

@wolbersm
Copy link
Collaborator

At the moment, analyse() and pool() just look at univariate estimates (plus se, df) and pool them one-by-one.
However, for several analyses (e.g. subgroup analyses, multi-arm trials with Dunnett's adjustment, Fieller's CI for ratios etc), it would be useful to be able to have two functions:

  • analyse_pars() where the output from each imputed dataset is a vector of estimates (plus corresponding covariance matrix)
  • pool_pars() which pools estimates (plus covariance matrices) across imputed datasets
@wolbersm wolbersm added the To be evaluated issues that must be discussed whether/how they have to be implemented label Mar 10, 2022
@gowerc
Copy link
Collaborator

gowerc commented Apr 20, 2022

My personal preference would be to integrate this functionality into the existing analyse/pool functions as opposed to creating a duplicate pair. Perhaps as either a flag option or method dispatch based on the input. This is something we can look into / consider though.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
To be evaluated issues that must be discussed whether/how they have to be implemented
Projects
None yet
Development

No branches or pull requests

3 participants