{"id":{"repo_id":"athens","oai_identifier":"oai:lib.uoa.gr:uoadl:1314720"},"canonical_url":"https://search.ndltd.org/etd/athens/oai:lib.uoa.gr:uoadl:1314720","repository":{"repo_id":"athens","name":"National and Kapodistrian University of Athens","base_url":"https://pergamos.lib.uoa.gr/uoa/dl/frontend/oaipmh"},"display":{"title":"Composite scores and health outcomes: Further investigation of the estimated associations","abstract":"In recent epidemiological studies, a common way of handling multiple risk factors, is to combine them into a new variable namely a “composite” which is quantified through a mathematical formula applied on the original risk factors. It has been shown in [1], that the estimated association between a composite and a continuous health outcome is a weighted average of the associations between the components of the composite and the outcome, the weights depending on the covariance matrix of the components. This project extends the indicated work by investigating whether the implemented formulas in [1] are also applicable for binary outcomes. We carried out simulations under the following scenarios: for Y the distributions of success were: random, 5%, 10%, 30%, 50%, 90%. For X_{j}, X we considered: (1) Binary X_{j} with distributions of success: 25%, 50%, 75%; X=\\sum_{j=1}^pX_{j}, and (2) X_{j}continuous with pre-specified \\cite{bamia2015anatomy} or non-pre-specified covariance matrix; X=\\sum_{j=1}^p(a_{j}X_{j}) with a_{j} arbitrary (e.g.as in [1]). Results suggested that the formula in [1] applies also for binary data. [1] Bamia, C. and Trichopoulos, D., 2015.An anatomy of the way composite scores work. European journal of epidemiology, 30(6), pp.473-483.","abstract_html":"In recent epidemiological studies, a common way of handling multiple risk factors, is to combine them into a new variable namely a “composite” which is quantified through a mathematical formula applied on the original risk factors. It has been shown in [1], that the estimated association between a composite and a continuous health outcome is a weighted average of the associations between the components of the composite and the outcome, the weights depending on the covariance matrix of the components. This project extends the indicated work by investigating whether the implemented formulas in [1] are also applicable for binary outcomes. We carried out simulations under the following scenarios: for Y the distributions of success were: random, 5%, 10%, 30%, 50%, 90%. For X_{j}, X we considered: (1) Binary X_{j} with distributions of success: 25%, 50%, 75%; X=\\sum_{j=1}^pX_{j}, and (2) X_{j}continuous with pre-specified \\cite{bamia2015anatomy} or non-pre-specified covariance matrix; X=\\sum_{j=1}^p(a_{j}X_{j}) with a_{j} arbitrary (e.g.as in [1]). Results suggested that the formula in [1] applies also for binary data. [1] Bamia, C. and Trichopoulos, D., 2015.An anatomy of the way composite scores work. European journal of epidemiology, 30(6), pp.473-483.","abstract_has_math":false,"creators":["Χριστοδούλου Ευαγγελία"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2016,"date_issued":"2016","date_published":"2016","updated_at":"2026-11-19T05:23:53Z","subjects":[],"languages":["English"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["uoadl:1314720"],"render_values":[{"text":"uoadl:1314720","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://pergamos.lib.uoa.gr/uoa/dl/object/1314720","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://pergamos.lib.uoa.gr/uoa/dl/object/1314720","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://pergamos.lib.uoa.gr/uoa/dl/frontend/oaipmh?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Alib.uoa.gr%3Auoadl%3A1314720","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Χριστοδούλου Ευαγγελία"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2016"]},{"key":"dc:type","label":"Dc Type","values":["born_digital_postgraduate_thesis","Διπλωματική Εργασία","Postgraduate Thesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["uoadl:1314720","https://pergamos.lib.uoa.gr/uoa/dl/object/1314720"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["In recent epidemiological studies, a common way of handling multiple risk factors, is to combine them into a new variable namely a “composite” which is quantified through a mathematical formula applied on the original risk factors. It has been shown in [1], that the estimated association between a composite and a continuous health outcome is a weighted average of the associations between the components of the composite and the outcome, the weights depending on the covariance matrix of the components. This project extends the indicated work by investigating whether the implemented formulas in [1] are also applicable for binary outcomes. We carried out simulations under the following scenarios: for Y the distributions of success were: random, 5%, 10%, 30%, 50%, 90%. For X_{j}, X we considered: (1) Binary X_{j} with distributions of success: 25%, 50%, 75%; X=\\sum_{j=1}^pX_{j}, and (2) X_{j}continuous with pre-specified \\cite{bamia2015anatomy} or non-pre-specified covariance matrix; X=\\sum_{j=1}^p(a_{j}X_{j}) with a_{j} arbitrary (e.g.as in [1]). Results suggested that the formula in [1] applies also for binary data. [1] Bamia, C. and Trichopoulos, D., 2015.An anatomy of the way composite scores work. European journal of epidemiology, 30(6), pp.473-483."]},{"key":"dc:title","label":"Title","values":["Composite scores and health outcomes: Further investigation of the estimated associations"]}]}],"canonical_facts":{"dc:creator":["Χριστοδούλου Ευαγγελία"],"dc:date":["2016"],"dc:description":["In recent epidemiological studies, a common way of handling multiple risk factors, is to combine them into a new variable namely a “composite” which is quantified through a mathematical formula applied on the original risk factors. It has been shown in [1], that the estimated association between a composite and a continuous health outcome is a weighted average of the associations between the components of the composite and the outcome, the weights depending on the covariance matrix of the components. This project extends the indicated work by investigating whether the implemented formulas in [1] are also applicable for binary outcomes. We carried out simulations under the following scenarios: for Y the distributions of success were: random, 5%, 10%, 30%, 50%, 90%. For X_{j}, X we considered: (1) Binary X_{j} with distributions of success: 25%, 50%, 75%; X=\\sum_{j=1}^pX_{j}, and (2) X_{j}continuous with pre-specified \\cite{bamia2015anatomy} or non-pre-specified covariance matrix; X=\\sum_{j=1}^p(a_{j}X_{j}) with a_{j} arbitrary (e.g.as in [1]). Results suggested that the formula in [1] applies also for binary data. [1] Bamia, C. and Trichopoulos, D., 2015.An anatomy of the way composite scores work. European journal of epidemiology, 30(6), pp.473-483."],"dc:identifier":["uoadl:1314720","https://pergamos.lib.uoa.gr/uoa/dl/object/1314720"],"dc:language":["English"],"dc:title":["Composite scores and health outcomes: Further investigation of the estimated associations"],"dc:type":["born_digital_postgraduate_thesis","Διπλωματική Εργασία","Postgraduate Thesis"]},"updated_at":"2026-11-19T05:23:53Z"}