Improving Power by Conditioning on Less in Post-selection Inference for Changepoints

Improving Power by Conditioning on Less in Post-selection Inference for Changepoints | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Improving Power by Conditioning on Less in Post-selection Inference for Changepoints Rachel Carrington, Paul Fearnhead This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3872789/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 04 Dec, 2024 Read the published version in Statistics and Computing → Version 1 posted 9 You are reading this latest preprint version Abstract Post-selection inference has recently been proposed as a way of quantifying uncertainty about detected changepoints. The idea is to run a changepoint detection algorithm, and then re-use the same data to perform a test for a change near each of the detected changes. By defining the p-value for the test appropriately, so that it is conditional on the information used to choose the test, this approach will produce valid p-values. We show how to improve the power of these procedures by conditioning on less information. This gives rise to an ideal post-selection p-value that is intractable but can be approximated by Monte Carlo. We show that for any Monte Carlo sample size, this procedure produces valid p-values, and empirically that noticeable increase in power is possible with only very modest Monte Carlo sample sizes. Our procedure is easy to implement given existing post-selection inference methods, as we just need to generate perturbations of the data set and re-apply the post-selection method to each of these. On genomic data consisting of human GC content, our procedure increases the number of significant changepoints that are detected when compared to the method of Jewell et al. (2022). Binary segmentation Breakpoint Fused Lasso Penalised likelihood Post-Selection p-value Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 04 Dec, 2024 Read the published version in Statistics and Computing → Version 1 posted Editorial decision: Revision requested 01 Jun, 2024 Reviews received at journal 26 May, 2024 Reviews received at journal 24 Mar, 2024 Reviewers agreed at journal 28 Jan, 2024 Reviewers agreed at journal 27 Jan, 2024 Reviewers invited by journal 26 Jan, 2024 Editor assigned by journal 18 Jan, 2024 Submission checks completed at journal 18 Jan, 2024 First submitted to journal 17 Jan, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-3872789","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":267959380,"identity":"db140ece-5fa9-414a-a6d3-ba87366c8f69","order_by":0,"name":"Rachel Carrington","email":"data:image/png;base64,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","orcid":"","institution":"Lancaster University","correspondingAuthor":true,"prefix":"","firstName":"Rachel","middleName":"","lastName":"Carrington","suffix":""},{"id":267959381,"identity":"49a108fc-a389-4c22-a206-3e9c47d88710","order_by":1,"name":"Paul Fearnhead","email":"","orcid":"","institution":"Lancaster University","correspondingAuthor":false,"prefix":"","firstName":"Paul","middleName":"","lastName":"Fearnhead","suffix":""}],"badges":[],"createdAt":"2024-01-17 11:44:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3872789/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3872789/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11222-024-10542-1","type":"published","date":"2024-12-04T15:58:05+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":70965317,"identity":"41389911-f09a-4714-a548-d5dbb8c1de87","added_by":"auto","created_at":"2024-12-09 16:19:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6159245,"visible":true,"origin":"","legend":"","description":"","filename":"PostselectionInferenceChangepoints.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3872789/v1_covered_963b19c1-4e0c-4e4d-acab-131b70acec3d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Improving Power by Conditioning on Less in Post-selection Inference for Changepoints","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"statistics-and-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"stco","sideBox":"Learn more about [Statistics and Computing](http://link.springer.com/journal/11222)","snPcode":"11222","submissionUrl":"https://submission.nature.com/new-submission/11222/3","title":"Statistics and Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Binary segmentation, Breakpoint, Fused Lasso, Penalised likelihood, Post-Selection p-value","lastPublishedDoi":"10.21203/rs.3.rs-3872789/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3872789/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Post-selection inference has recently been proposed as a way of quantifying uncertainty about detected changepoints. The idea is to run a changepoint detection algorithm, and then re-use the same data to perform a test for a change near each of the detected changes. By defining the p-value for the test appropriately, so that it is conditional on the information used to choose the test, this approach will produce valid p-values. We show how to improve the power of these procedures by conditioning on less information. This gives rise to an ideal post-selection p-value that is intractable but can be approximated by Monte Carlo. We show that for any Monte Carlo sample size, this procedure produces valid p-values, and empirically that noticeable increase in power is possible with only very modest Monte Carlo sample sizes. Our procedure is easy to implement given existing post-selection inference methods, as we just need to generate perturbations of the data set and re-apply the post-selection method to each of these. On genomic data consisting of human GC content, our procedure increases the number of significant changepoints that are detected when compared to the method of Jewell et al. (2022).","manuscriptTitle":"Improving Power by Conditioning on Less in Post-selection Inference for Changepoints","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-19 20:26:37","doi":"10.21203/rs.3.rs-3872789/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-06-01T11:35:39+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-26T20:07:51+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-03-24T13:00:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"d7aa1e62-88ab-4f06-9bbe-1f883737a796","date":"2024-01-28T18:22:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"8269757d-af9e-47a4-a157-9d6e3a8d926c","date":"2024-01-27T17:18:25+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-01-27T02:23:13+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-01-19T02:45:55+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-01-18T08:00:58+00:00","index":"","fulltext":""},{"type":"submitted","content":"Statistics and Computing","date":"2024-01-17T11:42:07+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"statistics-and-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"stco","sideBox":"Learn more about [Statistics and Computing](http://link.springer.com/journal/11222)","snPcode":"11222","submissionUrl":"https://submission.nature.com/new-submission/11222/3","title":"Statistics and Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"b89d5f4e-00bd-43e5-b5a4-a45ac25b098a","owner":[],"postedDate":"January 19th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-12-09T16:12:36+00:00","versionOfRecord":{"articleIdentity":"rs-3872789","link":"https://doi.org/10.1007/s11222-024-10542-1","journal":{"identity":"statistics-and-computing","isVorOnly":false,"title":"Statistics and Computing"},"publishedOn":"2024-12-04 15:58:05","publishedOnDateReadable":"December 4th, 2024"},"versionCreatedAt":"2024-01-19 20:26:37","video":"","vorDoi":"10.1007/s11222-024-10542-1","vorDoiUrl":"https://doi.org/10.1007/s11222-024-10542-1","workflowStages":[]},"version":"v1","identity":"rs-3872789","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3872789","identity":"rs-3872789","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}