{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GY5PNVZM3MANDL6TC2D72KPDWF","short_pith_number":"pith:GY5PNVZM","schema_version":"1.0","canonical_sha256":"363af6d72cdb00d1afd31687fd29e3b1461603c519642b01807938df71a98d9b","source":{"kind":"arxiv","id":"2603.24814","version":3},"attestation_state":"computed","paper":{"title":"Multiple-group (Controlled) Interrupted Time Series Analysis with Higher-Order Autoregressive Errors: A Simulation Study Comparing Newey-West and Prais-Winsten Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Prais-Winsten regression provides valid inference under higher-order autoregressive errors in multiple-group interrupted time series analysis while OLS with Newey-West errors does not.","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Ariel Linden","submitted_at":"2026-03-25T20:52:35Z","abstract_excerpt":"Previous comparisons of ordinary least squares with Newey-West standard errors (OLS-NW) and Prais-Winsten (PW) regression in multiple-group interrupted time series analysis have been limited to first-order autoregressive (AR[1]) errors because PW estimation for higher-order AR[k] processes was previously unavailable. We conducted the first systematic evaluation of OLS-NW and PW under AR[2] and AR[3] error structures using Monte Carlo simulation. Simulations examined mild positive, oscillatory, and high persistent autocorrelation across varying series lengths and effect sizes. OLS-NW generally "},"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":"2603.24814","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-03-25T20:52:35Z","cross_cats_sorted":[],"title_canon_sha256":"132cf6379996a4dbb25a6e39a7f6935ed85b7a5e15a1ccb829724b27da20238c","abstract_canon_sha256":"a24b5f8058b2f187c6a4f34df58302701b1c423b246ebb3b60eea0ee2828e72e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:28.793042Z","signature_b64":"HiR84jMxHSgtJ9ADi66Cc8RT6L9WmCMwsIc1ndmuI3+LuEsj9uwQgr9UYF4lisLzXVy4mwCUvOJkjA68W3gqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"363af6d72cdb00d1afd31687fd29e3b1461603c519642b01807938df71a98d9b","last_reissued_at":"2026-05-26T01:03:28.792137Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:28.792137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiple-group (Controlled) Interrupted Time Series Analysis with Higher-Order Autoregressive Errors: A Simulation Study Comparing Newey-West and Prais-Winsten Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Prais-Winsten regression provides valid inference under higher-order autoregressive errors in multiple-group interrupted time series analysis while OLS with Newey-West errors does not.","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Ariel Linden","submitted_at":"2026-03-25T20:52:35Z","abstract_excerpt":"Previous comparisons of ordinary least squares with Newey-West standard errors (OLS-NW) and Prais-Winsten (PW) regression in multiple-group interrupted time series analysis have been limited to first-order autoregressive (AR[1]) errors because PW estimation for higher-order AR[k] processes was previously unavailable. We conducted the first systematic evaluation of OLS-NW and PW under AR[2] and AR[3] error structures using Monte Carlo simulation. Simulations examined mild positive, oscillatory, and high persistent autocorrelation across varying series lengths and effect sizes. OLS-NW generally "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The tradeoff between power and valid inference seen under AR1 errors worsens with higher order autocorrelation. Under highly persistent autocorrelation, OLS-NW coverage fell to 45 to 50 percent at 100 time points, while PW maintained 91 to 94 percent coverage. PW provides more reliable inference and is preferred for hypothesis testing and error control.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The specific AR2 and AR3 parameterizations used in the simulations (mild, oscillatory, highly persistent) are representative of autocorrelation structures encountered in actual multiple-group healthcare time series data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Prais-Winsten regression maintains valid inference under AR2 and AR3 errors in MG-ITSA simulations, while Newey-West shows inflated type I error rates up to 57% and coverage as low as 45%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Prais-Winsten regression provides valid inference under higher-order autoregressive errors in multiple-group interrupted time series analysis while OLS with Newey-West errors does not.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2ca3ef0fbc403e4490de1a899c1fb75da03334ed2ac7cc446a6dc92c8e442e37"},"source":{"id":"2603.24814","kind":"arxiv","version":3},"verdict":{"id":"cbd0cdaf-4bfe-4553-876e-4049668aacef","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T00:07:26.198752Z","strongest_claim":"The tradeoff between power and valid inference seen under AR1 errors worsens with higher order autocorrelation. Under highly persistent autocorrelation, OLS-NW coverage fell to 45 to 50 percent at 100 time points, while PW maintained 91 to 94 percent coverage. PW provides more reliable inference and is preferred for hypothesis testing and error control.","one_line_summary":"Prais-Winsten regression maintains valid inference under AR2 and AR3 errors in MG-ITSA simulations, while Newey-West shows inflated type I error rates up to 57% and coverage as low as 45%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The specific AR2 and AR3 parameterizations used in the simulations (mild, oscillatory, highly persistent) are representative of autocorrelation structures encountered in actual multiple-group healthcare time series data.","pith_extraction_headline":"Prais-Winsten regression provides valid inference under higher-order autoregressive errors in multiple-group interrupted time series analysis while OLS with Newey-West errors does not."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.24814/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":"2603.24814","created_at":"2026-05-26T01:03:28.792242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.24814v3","created_at":"2026-05-26T01:03:28.792242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.24814","created_at":"2026-05-26T01:03:28.792242+00:00"},{"alias_kind":"pith_short_12","alias_value":"GY5PNVZM3MAN","created_at":"2026-05-26T01:03:28.792242+00:00"},{"alias_kind":"pith_short_16","alias_value":"GY5PNVZM3MANDL6T","created_at":"2026-05-26T01:03:28.792242+00:00"},{"alias_kind":"pith_short_8","alias_value":"GY5PNVZM","created_at":"2026-05-26T01:03:28.792242+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/GY5PNVZM3MANDL6TC2D72KPDWF","json":"https://pith.science/pith/GY5PNVZM3MANDL6TC2D72KPDWF.json","graph_json":"https://pith.science/api/pith-number/GY5PNVZM3MANDL6TC2D72KPDWF/graph.json","events_json":"https://pith.science/api/pith-number/GY5PNVZM3MANDL6TC2D72KPDWF/events.json","paper":"https://pith.science/paper/GY5PNVZM"},"agent_actions":{"view_html":"https://pith.science/pith/GY5PNVZM3MANDL6TC2D72KPDWF","download_json":"https://pith.science/pith/GY5PNVZM3MANDL6TC2D72KPDWF.json","view_paper":"https://pith.science/paper/GY5PNVZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.24814&json=true","fetch_graph":"https://pith.science/api/pith-number/GY5PNVZM3MANDL6TC2D72KPDWF/graph.json","fetch_events":"https://pith.science/api/pith-number/GY5PNVZM3MANDL6TC2D72KPDWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GY5PNVZM3MANDL6TC2D72KPDWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GY5PNVZM3MANDL6TC2D72KPDWF/action/storage_attestation","attest_author":"https://pith.science/pith/GY5PNVZM3MANDL6TC2D72KPDWF/action/author_attestation","sign_citation":"https://pith.science/pith/GY5PNVZM3MANDL6TC2D72KPDWF/action/citation_signature","submit_replication":"https://pith.science/pith/GY5PNVZM3MANDL6TC2D72KPDWF/action/replication_record"}},"created_at":"2026-05-26T01:03:28.792242+00:00","updated_at":"2026-05-26T01:03:28.792242+00:00"}