{"corpus_id":41046748,"paper_sha":"37210786883661c9acff51c6ca0e70bc50296e7a","doi":"10.1016/J.JSPI.2021.05.005","arxiv_id":"2204.05615","pmid":null,"pmcid":null,"mag_id":3175174529,"dblp_id":null,"acl_id":null,"title":"Normalized Power Prior Bayesian Analysis","year":2022,"publication_date":"2022-04-12","venue":"","journal":{"name":"","pages":null,"volume":""},"journal_issn":null,"journal_title":null,"publication_types":[],"pubmed_pub_types":null,"s2_fields_of_study":["Mathematics","Computer Science"],"reference_count":29,"citation_count":28,"influential_citation_count":4,"is_open_access":true,"arxiv_categories":["stat.ME","stat.AP"],"arxiv_license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":"https://arxiv.org/pdf/2204.05615","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/37210786883661c9acff51c6ca0e70bc50296e7a","s2_open_access_license":null,"s2_open_access_status":"GREEN","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"The elicitation of power prior distributions is based on the availability of historical data, and is realized by raising the likelihood function of the historical data to a fractional power. However, an arbitrary positive constant before the like- lihood function of the historical data could change the inferential results when one uses the original power prior. This raises a question that which likelihood function should be used, one from raw data, or one from a su±cient-statistics. We propose a normalized power prior that can better utilize the power parameter in quantifying the heterogeneity between current and historical data. Furthermore, when the power parameter is random, the optimality of the normalized power priors is shown in the sense of maximizing Shannon's mutual information. Some comparisons between the original and the normalized power prior approaches are made and a water-quality monitoring data is used to show that the normalized power prior is more sensible.","claims":[{"public_id":"cl_f39606dce8b077c50eacbcd710627fcf","status":"active","text":"A normalized power prior is proposed to better use the power parameter for quantifying heterogeneity between current and historical data.","confidence":0.95,"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_f39606dce8b077c50eacbcd710627fcf"},{"public_id":"cl_d9801921c83aba1c430184ac0b2c7be4","status":"active","text":"An arbitrary positive constant before the likelihood function of the historical data can change inferential results under the original power prior.","confidence":0.93,"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_d9801921c83aba1c430184ac0b2c7be4"},{"public_id":"cl_8b41196f41c0016dec9a4792d4b6ced7","status":"active","text":"Comparisons and a water-quality monitoring data application indicate that the normalized power prior is more sensible than the original power prior approach.","confidence":0.86,"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_8b41196f41c0016dec9a4792d4b6ced7"},{"public_id":"cl_2cf93baa039c96dbcf8c18657227c5b8","status":"active","text":"When the power parameter is random, normalized power priors are optimal in the sense of maximizing Shannon's mutual information.","confidence":0.94,"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_2cf93baa039c96dbcf8c18657227c5b8"}],"concepts":[{"public_id":"co_1c45017cbda8968bdec5290665f58b8f","status":"active","name":"heterogeneity between current and historical data","description":"The degree of difference between current data and historical data quantified through the power parameter.","types":["statistical property"],"aliases":[],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1c45017cbda8968bdec5290665f58b8f"},{"public_id":"co_5059e07eaa32865b1c4e0ce8fdca685e","status":"active","name":"normalized power prior","description":"A power prior formulation that normalizes the powered historical-data likelihood.","types":["prior method"],"aliases":["normalized power priors"],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_5059e07eaa32865b1c4e0ce8fdca685e"},{"public_id":"co_806ee8de15a2d9e1d329de50c0ee0307","status":"active","name":"arbitrary positive constant","description":"A multiplicative constant placed before the historical-data likelihood that can affect original power prior inference.","types":["modeling factor"],"aliases":[],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_806ee8de15a2d9e1d329de50c0ee0307"},{"public_id":"co_838d3eabb52f15b3d93e72872806929b","status":"active","name":"Shannon's mutual information","description":"An information-theoretic quantity used to state the optimality of normalized power priors.","types":["information measure"],"aliases":[],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_838d3eabb52f15b3d93e72872806929b"},{"public_id":"co_8746799e8043df5d5d4c37522f96ba27","status":"active","name":"sufficient-statistics","description":"A summarized data representation considered as an alternative basis for the likelihood function.","types":["data representation"],"aliases":[],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_8746799e8043df5d5d4c37522f96ba27"},{"public_id":"co_a5576e33adae787200fe85233b2da780","status":"active","name":"power prior distributions","description":"Prior distributions elicited from historical data by powering the historical-data likelihood.","types":["prior distribution"],"aliases":[],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_a5576e33adae787200fe85233b2da780"},{"public_id":"co_aa12236522c9e39e774768072432ef4a","status":"active","name":"likelihood function of the historical data","description":"The likelihood contribution from historical observations used in power prior construction.","types":["statistical function"],"aliases":[],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_aa12236522c9e39e774768072432ef4a"},{"public_id":"co_b2fc64acc6f28e21543947fded23fcf2","status":"active","name":"power parameter","description":"The parameter controlling how much influence historical data has in the power prior.","types":["model parameter"],"aliases":[],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_b2fc64acc6f28e21543947fded23fcf2"},{"public_id":"co_ba579baada036cd122758f5e9ece0c0e","status":"active","name":"fractional power","description":"The exponent applied to the historical-data likelihood in a power prior.","types":["weighting mechanism"],"aliases":[],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ba579baada036cd122758f5e9ece0c0e"},{"public_id":"co_ce4a1ce6bdea2e8a887c0055546aaacd","status":"active","name":"original power prior","description":"The baseline power prior formulation discussed as sensitive to likelihood scaling choices.","types":["prior method"],"aliases":[],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ce4a1ce6bdea2e8a887c0055546aaacd"},{"public_id":"co_e81d9fc23de36ad568e32e2fab8dd32b","status":"active","name":"historical data","description":"Previously available data used to construct power prior distributions.","types":["data source"],"aliases":[],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_e81d9fc23de36ad568e32e2fab8dd32b"},{"public_id":"co_ede9fd691612ec65908a9678422a5892","status":"active","name":"water-quality monitoring data","description":"An applied dataset used to illustrate the normalized power prior approach.","types":["dataset"],"aliases":[],"contributors":[{"id":35,"public_id":"b2adb6bfad","public_label":"Anonymous (b2adb6bfad)","roles":["extraction"],"url":"https://sah.borca.ai/u/b2adb6bfad"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ede9fd691612ec65908a9678422a5892"}],"external_ids":{"DOI":"10.1016/J.JSPI.2021.05.005","ArXiv":"2204.05615","PubMed":null,"PubMedCentral":null,"MAG":3175174529,"DBLP":null,"ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://arxiv.org/pdf/2204.05615","landing_url":"https://www.semanticscholar.org/paper/37210786883661c9acff51c6ca0e70bc50296e7a","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":null,"status":"GREEN","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":true,"full_text_source":"arxiv","count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":630810,"paper_uid":"a1c8065d-a643-4a80-aa5c-a406af2166a5","canonical_identity":{"paper_id":630810,"paper_uid":"a1c8065d-a643-4a80-aa5c-a406af2166a5","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/41046748"}