Add survival analysis and competing risks integration#229
Open
xushenbo wants to merge 1 commit intoDoubleML:mainfrom
Open
Add survival analysis and competing risks integration#229xushenbo wants to merge 1 commit intoDoubleML:mainfrom
xushenbo wants to merge 1 commit intoDoubleML:mainfrom
Conversation
- DoubleMLSurvival, DoubleMLSurvivalProb, DoubleMLRMST: survival probability and RMST estimation with doubly-robust EIF, SuperLearner/survSuperLearner - DoubleMLCompeting, DoubleMLCIFJ, DoubleMLRMTLJ: competing risks CIF and RMTL with separable direct/indirect effects (A*=1 and A*=0) - Simultaneous confidence bands via Gaussian multiplier bootstrap (get_inference_curve, get_inference_curve_sep_*) - inference_point.R, inference_curve.R: EIF-based point and curve inference - survival_nuisance.R: cross-fitted S/G nuisance via survSuperLearner - Tests for all 4 classes; makeCluster(2) for CRAN compliance - devtools::check() passes: 0 errors, 0 warnings Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Author
|
@PhilippBach PR is ready for an initial review. Happy to discuss any structural or implementation questions. |
Member
|
Hi @xushenbo thank you for opening the PR, we'll go through it and come back to you if there are some fixed to be done. Thanks for contibuting to DoubleML! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR integrates survival analysis and competing risks estimation into the DoubleML R package, using the SuperLearner/survSuperLearner framework for nuisance function estimation.
New classes
DoubleMLSurvival— abstract base class for survival modelsDoubleMLSurvivalProb— survival probability ATE at time τDoubleMLRMST— restricted mean survival time (RMST) ATE up to τDoubleMLCompeting— abstract base class for competing risks modelsDoubleMLCIFJ— cumulative incidence function (CIF) ATE for cause j at time τDoubleMLRMTLJ— restricted mean time lost (RMTL) ATE for cause j up to τKey features
get_inference_curve(npath=))get_separable_*,get_inference_curve_sep_*)New infrastructure files
R/inference_point.R— EIF-based point estimationR/inference_curve.R— simultaneous confidence band computationR/survival_nuisance.R— cross-fitted S/G nuisance estimationR/dataset_censored.R— DGP helpers for survival and competing risks dataTests
tests/testthat/test-double_ml_rmst.Rtests/testthat/test-double_ml_survival_prob.Rtests/testthat/test-double_ml_cifj.Rtests/testthat/test-double_ml_rmtlj.RAll tests use real ML (SuperLearner/survSuperLearner), cross-fitting with
n_folds=2, andmakeCluster(2)for CRAN compliance (_R_CHECK_LIMIT_CORES_=TRUE).Test plan
devtools::check()— 0 errors, 0 warnings, 2 pre-existing notesdevtools::test()— FAIL 0, PASS 2644, SKIP 4styler::style_pkg(style = styler.mlr::mlr_style)applieddevtools::document()— docs regenerated, no warnings🤖 Generated with Claude Code