{"doi":"10.1101/2025.10.08.674881","title":"Replicability of multivariate brain-behaviour associations depends on clinical profile","abstract":"Recent work suggests that thousands of individuals are required in multivariate brain-behaviour analyses to obtain consistently replicable results. Some believe, however, that smaller sample sizes may be sufficient if specific subpopulations are targeted. We investigated how sample size and cohort composition influence the replicability of Canonical Correlation Analysis (CCA) results using the UK Biobank (N=40,514). We applied CCA to diffusion-weighted magnetic resonance imaging (dMRI) phenotypes and cognitive assessment test scores. We defined four participant cohorts based on clinical profile and found that, across all cohorts, sample sizes of around 500 were needed to obtain replicable canonical correlations and variable loadings. The most targeted cohort required much fewer samples to achieve similar or greater correlations than the other cohorts. Variable loadings were consistent between sample sizes of ~500 to thousands, suggesting that sample sizes in the order of hundreds may be sufficient for obtaining reliable CCA results.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2025,"id":577383,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9294,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":568275,"name":"Brent McPherson","orcid":"0000-0001-8378-8136","position":1,"is_corresponding":false},{"id":34560,"name":"Bratislav Misic","orcid":"0000-0003-0307-2862","position":2,"is_corresponding":false},{"id":64562,"name":"Franco Pestilli","orcid":"0000-0002-2469-0494","position":3,"is_corresponding":false},{"id":304553,"name":"Celia M.T. Greenwood","orcid":"0000-0002-2427-5696","position":4,"is_corresponding":false},{"id":60908,"name":"Jean‐Baptiste Poline","orcid":"0000-0002-9794-749X","position":5,"is_corresponding":false},{"id":1421151,"name":"Michelle Wang","orcid":"0000-0002-3432-6899","position":0,"is_corresponding":true}],"reference_count":0,"raw_metadata":null,"created_at":"2026-07-19T02:58:04.622308Z","pmid":"41280025","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}