{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NEF2S65FHU4NMNWZHE6OIDER5I","short_pith_number":"pith:NEF2S65F","schema_version":"1.0","canonical_sha256":"690ba97ba53d38d636d9393ce40c91ea28fab70ea946357791becfd22db5c94e","source":{"kind":"arxiv","id":"2310.17434","version":2},"attestation_state":"computed","paper":{"title":"The `Why' behind including `Y' in your imputation model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"stat.ME","authors_text":"Lucy D'Agostino McGowan, Sarah C. Lotspeich, Staci A. Hepler","submitted_at":"2023-10-26T14:43:36Z","abstract_excerpt":"Missing data is a common challenge when analyzing epidemiological data, and imputation is often used to address this issue. Here, we investigate the scenario where a covariate used in an analysis has missingness and will be imputed. There are recommendations to include the outcome from the analysis model in the imputation model for missing covariates, but it is not necessarily clear if this recommendation always holds and why this is sometimes true. We examine deterministic imputation (i.e., single imputation with fixed values) and stochastic imputation (i.e., single or multiple imputation wit"},"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":"2310.17434","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2023-10-26T14:43:36Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"280e530432ba9be0fea5859acd84e7c805ed0cc9844e2c339258ac1237d9b505","abstract_canon_sha256":"d014d559dd3c7fb0ca2f1487563f4aac75e69a92157e0df56b01633e97b81f86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:53.377116Z","signature_b64":"htLH5mWRp05/bdIStdU5sOLsM8UTEFONP9aPrBi7drGvceZjUdxIfs+wPW03Adr1KOkWp9BPVD1aN5vUoWk8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"690ba97ba53d38d636d9393ce40c91ea28fab70ea946357791becfd22db5c94e","last_reissued_at":"2026-07-05T07:50:53.376664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:53.376664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The `Why' behind including `Y' in your imputation model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"stat.ME","authors_text":"Lucy D'Agostino McGowan, Sarah C. Lotspeich, Staci A. Hepler","submitted_at":"2023-10-26T14:43:36Z","abstract_excerpt":"Missing data is a common challenge when analyzing epidemiological data, and imputation is often used to address this issue. Here, we investigate the scenario where a covariate used in an analysis has missingness and will be imputed. There are recommendations to include the outcome from the analysis model in the imputation model for missing covariates, but it is not necessarily clear if this recommendation always holds and why this is sometimes true. We examine deterministic imputation (i.e., single imputation with fixed values) and stochastic imputation (i.e., single or multiple imputation wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17434","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/2310.17434/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":"2310.17434","created_at":"2026-07-05T07:50:53.376720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17434v2","created_at":"2026-07-05T07:50:53.376720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17434","created_at":"2026-07-05T07:50:53.376720+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEF2S65FHU4N","created_at":"2026-07-05T07:50:53.376720+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEF2S65FHU4NMNWZ","created_at":"2026-07-05T07:50:53.376720+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEF2S65F","created_at":"2026-07-05T07:50:53.376720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.10113","citing_title":"Asymptotics of Nonparametric Estimation under General Non-monotone MAR Missingness: A Nonparametric Maximum Likelihood Approach","ref_index":101,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NEF2S65FHU4NMNWZHE6OIDER5I","json":"https://pith.science/pith/NEF2S65FHU4NMNWZHE6OIDER5I.json","graph_json":"https://pith.science/api/pith-number/NEF2S65FHU4NMNWZHE6OIDER5I/graph.json","events_json":"https://pith.science/api/pith-number/NEF2S65FHU4NMNWZHE6OIDER5I/events.json","paper":"https://pith.science/paper/NEF2S65F"},"agent_actions":{"view_html":"https://pith.science/pith/NEF2S65FHU4NMNWZHE6OIDER5I","download_json":"https://pith.science/pith/NEF2S65FHU4NMNWZHE6OIDER5I.json","view_paper":"https://pith.science/paper/NEF2S65F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17434&json=true","fetch_graph":"https://pith.science/api/pith-number/NEF2S65FHU4NMNWZHE6OIDER5I/graph.json","fetch_events":"https://pith.science/api/pith-number/NEF2S65FHU4NMNWZHE6OIDER5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEF2S65FHU4NMNWZHE6OIDER5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEF2S65FHU4NMNWZHE6OIDER5I/action/storage_attestation","attest_author":"https://pith.science/pith/NEF2S65FHU4NMNWZHE6OIDER5I/action/author_attestation","sign_citation":"https://pith.science/pith/NEF2S65FHU4NMNWZHE6OIDER5I/action/citation_signature","submit_replication":"https://pith.science/pith/NEF2S65FHU4NMNWZHE6OIDER5I/action/replication_record"}},"created_at":"2026-07-05T07:50:53.376720+00:00","updated_at":"2026-07-05T07:50:53.376720+00:00"}