{"paper":{"title":"Double/debiased machine learning of quantile treatment effects on long-term outcomes in clinical trials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A doubly robust estimator identifies quantile treatment effects on long-term outcomes by linking trial surrogates to external data.","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Niwen Zhou, Peng Wu, Xu Guo, Ziyang Liu","submitted_at":"2026-05-14T02:19:41Z","abstract_excerpt":"Long-term outcomes are often unavailable in randomized clinical trials, although short-term surrogate outcomes are commonly observed. External observational data may contain the long-term outcome, but causal comparisons based on such data alone are vulnerable to confounding. Existing surrogate-based data integration methods for long-term outcomes have focused primarily on average treatment effects. We study estimation of quantile treatment effects for long-term outcomes in the trial population by combining randomized trial data with external observational data. Under treatment randomization, p"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Under treatment randomization, positivity, and a surrogate-based transportability assumption, we establish identification and develop a doubly robust estimator for inference. The estimator accommodates flexible machine learning methods for nuisance estimation, remains consistent if either the score-related or outcome regression-related nuisance functions are consistently estimated, and is asymptotically normal under regularity conditions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The surrogate-based transportability assumption that permits linking short-term surrogates observed in the randomized trial to long-term outcomes in the external observational data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A doubly robust estimator is developed for quantile treatment effects on long-term outcomes by integrating randomized trial data with observational data under surrogate transportability, remaining consistent if either nuisance function is correctly estimated.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A doubly robust estimator identifies quantile treatment effects on long-term outcomes by linking trial surrogates to external data.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b7bca327ac8a58b51a4934fd1406bb57c5d545436eea522d94d6f671d571ace9"},"source":{"id":"2605.14275","kind":"arxiv","version":1},"verdict":{"id":"8f76fbb7-58ae-489b-ab07-2aa5cf1d9064","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:35:42.644855Z","strongest_claim":"Under treatment randomization, positivity, and a surrogate-based transportability assumption, we establish identification and develop a doubly robust estimator for inference. The estimator accommodates flexible machine learning methods for nuisance estimation, remains consistent if either the score-related or outcome regression-related nuisance functions are consistently estimated, and is asymptotically normal under regularity conditions.","one_line_summary":"A doubly robust estimator is developed for quantile treatment effects on long-term outcomes by integrating randomized trial data with observational data under surrogate transportability, remaining consistent if either nuisance function is correctly estimated.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The surrogate-based transportability assumption that permits linking short-term surrogates observed in the randomized trial to long-term outcomes in the external observational data.","pith_extraction_headline":"A doubly robust estimator identifies quantile treatment effects on long-term outcomes by linking trial surrogates to external data."},"references":{"count":33,"sample":[{"doi":"","year":2018,"title":"Double/debiased machine learning for treatment and structural parameters , author=. 2018 , publisher=","work_id":"8ccbab19-be51-4b8b-b547-d37977f8ca39","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Gaussian approximation of suprema of empirical processes , author=","work_id":"664ad426-5422-411b-b019-0b8cb00c0cbe","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1994,"title":"Handbook of econometrics , volume=","work_id":"8c8aad9f-0ead-4e5b-a389-2c69126aae34","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1996,"title":"Weak convergence , author=. 1996 , publisher=","work_id":"b5f9da6e-46d3-4a8c-b140-334bb90f1e84","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Inverting estimating equations for causal inference on quantiles , author=. Biometrika , volume=. 2025 , publisher=","work_id":"c7326007-98e1-440e-b552-a7b955bc902b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":33,"snapshot_sha256":"9bbf07b1708de9c9885cae07f38a01a7b85206101e02410bd093a61b9625d8bf","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}