{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U5TWAYCRDM7QCJMEKRDEFZLIXF","short_pith_number":"pith:U5TWAYCR","schema_version":"1.0","canonical_sha256":"a7676060511b3f012584544642e568b968f5f0828aec4bee09af53a0d86f7be5","source":{"kind":"arxiv","id":"2104.02769","version":2},"attestation_state":"computed","paper":{"title":"Variable selection with missing data in both covariates and outcomes: Imputation and machine learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"stat.ME","authors_text":"Jiayi Ji, Jung-Yi Joyce Lin, Liangyuan Hu","submitted_at":"2021-04-06T20:18:29Z","abstract_excerpt":"The missing data issue is ubiquitous in health studies. Variable selection in the presence of both missing covariates and outcomes is an important statistical research topic but has been less studied. Existing literature focuses on parametric regression techniques that provide direct parameter estimates of the regression model. Flexible nonparametric machine learning methods considerably mitigate the reliance on the parametric assumptions, but do not provide as naturally defined variable importance measure as the covariate effect native to parametric models. We investigate a general variable s"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2104.02769","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2021-04-06T20:18:29Z","cross_cats_sorted":["stat.AP","stat.ML"],"title_canon_sha256":"95f03967c0b9cfbb919651d3e9b87664c8343bff63360f536746e05ed716e955","abstract_canon_sha256":"2284176e65a91ffe90a407ee66f12c852412dbc5f54d08548b71f668e026352a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:04.852830Z","signature_b64":"P7Oraj36u4GLmInwfWYtxF6CNgDcEsZcQVHO95CUz7z0pV5LsDOLRFK5FTngx8uwhN0xmc8QYnOyR+E3lL9lDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7676060511b3f012584544642e568b968f5f0828aec4bee09af53a0d86f7be5","last_reissued_at":"2026-07-05T02:56:04.852392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:04.852392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variable selection with missing data in both covariates and outcomes: Imputation and machine learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"stat.ME","authors_text":"Jiayi Ji, Jung-Yi Joyce Lin, Liangyuan Hu","submitted_at":"2021-04-06T20:18:29Z","abstract_excerpt":"The missing data issue is ubiquitous in health studies. Variable selection in the presence of both missing covariates and outcomes is an important statistical research topic but has been less studied. Existing literature focuses on parametric regression techniques that provide direct parameter estimates of the regression model. Flexible nonparametric machine learning methods considerably mitigate the reliance on the parametric assumptions, but do not provide as naturally defined variable importance measure as the covariate effect native to parametric models. We investigate a general variable s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02769","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.02769/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2104.02769","created_at":"2026-07-05T02:56:04.852449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.02769v2","created_at":"2026-07-05T02:56:04.852449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02769","created_at":"2026-07-05T02:56:04.852449+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5TWAYCRDM7Q","created_at":"2026-07-05T02:56:04.852449+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5TWAYCRDM7QCJME","created_at":"2026-07-05T02:56:04.852449+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5TWAYCR","created_at":"2026-07-05T02:56:04.852449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5TWAYCRDM7QCJMEKRDEFZLIXF","json":"https://pith.science/pith/U5TWAYCRDM7QCJMEKRDEFZLIXF.json","graph_json":"https://pith.science/api/pith-number/U5TWAYCRDM7QCJMEKRDEFZLIXF/graph.json","events_json":"https://pith.science/api/pith-number/U5TWAYCRDM7QCJMEKRDEFZLIXF/events.json","paper":"https://pith.science/paper/U5TWAYCR"},"agent_actions":{"view_html":"https://pith.science/pith/U5TWAYCRDM7QCJMEKRDEFZLIXF","download_json":"https://pith.science/pith/U5TWAYCRDM7QCJMEKRDEFZLIXF.json","view_paper":"https://pith.science/paper/U5TWAYCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.02769&json=true","fetch_graph":"https://pith.science/api/pith-number/U5TWAYCRDM7QCJMEKRDEFZLIXF/graph.json","fetch_events":"https://pith.science/api/pith-number/U5TWAYCRDM7QCJMEKRDEFZLIXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5TWAYCRDM7QCJMEKRDEFZLIXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5TWAYCRDM7QCJMEKRDEFZLIXF/action/storage_attestation","attest_author":"https://pith.science/pith/U5TWAYCRDM7QCJMEKRDEFZLIXF/action/author_attestation","sign_citation":"https://pith.science/pith/U5TWAYCRDM7QCJMEKRDEFZLIXF/action/citation_signature","submit_replication":"https://pith.science/pith/U5TWAYCRDM7QCJMEKRDEFZLIXF/action/replication_record"}},"created_at":"2026-07-05T02:56:04.852449+00:00","updated_at":"2026-07-05T02:56:04.852449+00:00"}