search

alexpkeil1 / qgcomp

QGcomp (quantile g-computation): estimating the effects of exposure mixtures. Works for continuous, binary, and right-censored survival outcomes. Flexible, unconstrained, fast and guided by modern causal inference principles
27 stars 6 forks source link

Fitting a competing risks model #29

Closed sethfrnd closed 1 year ago

sethfrnd commented 1 year ago

This isn't a "bug" just a question of how estimating a competing risks model might be accomplished.

It seems that the Surv package in R doesn't do competing risks. For that, you have to use the cmprsk package. BUT then qgcomp can’t estimate a model created from cmprsk...

Is there a way around this?

Thank you for your help.

alexpkeil1 commented 1 year ago

Not sure I understand you’re after or what the concern is about the standard functionality. The survival package fits Cox models, multi state models, and a Fine-Gray model. All of those consider competing risks in various ways. That said, I’m not sure whether anything other than the standard Cox model plays nicely with qgcomp functions. I would love to hear back if you test the other approaches!On Mar 22, 2023, at 9:36 AM, sethfrnd @.***> wrote: This isn't a "bug" just a question of how estimating a competing risks model might be accomplished. It seems that the Surv package in R doesn't do competing risks. For that, you have to use the cmprsk package. BUT then qgcomp can’t estimate a model created from cmprsk... Is there a way around this? Thank you for your help.

—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you are subscribed to this thread.Message ID: @.***>

sethfrnd commented 1 year ago

I think my issue is really about fitting a Fine-Gray model with complex survey data and THEN applying it to qgcomp. I'm a bit ahead of myself. I'm closing this because I have to figure out those early steps first.

alexpkeil1 commented 1 year ago

Feel free to keep this open as an enhancement if the other approaches  don’t work out of the box. It’s a good idea to bring in other approaches to competing risks aside from the Cox model!On Mar 22, 2023, at 3:02 PM, sethfrnd @.***> wrote: Closed #29 as completed.

—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you commented.Message ID: @.***>