Network meta-analysis has been introduced as an extension of pairwise meta-analysis to facilitate indirect comparisons of multiple interventions that have not been studied in a head-to-head fashion. The use of network meta-analysis is becoming increasingly popular in biomedical sciences, especially in epidemiology and in clinical trials, where the safety and efficacy of a treatment is determined based on a series of studies with similar protocols. A search through medical journals revealed a lack of presentations of Bayesian models within a network meta-analysis framework and thus motivated further research into this combined area of study. The development of four hierarchical Bayesian models applicable to the field of network meta-analysis are presented. Two of them were constructed to estimate all possible drug-group comparisons, whereas the other two concentrate on estimating all pairwise drug comparisons. Moreover, the Bayesian models will also allow borrowing strength from other related studies. Two simulations demonstrating the capabilities of these models are also presented. The first simulation demonstrates the ability of the models to estimate all comparisons. The second simulation focuses on the models' abilities to estimate the overall mean comparison. The models are also applied to data provided in Liu et al.(2012) and the results compared to the bayesian network meta-analysis results presented by Liu et al.(2012).
","abstract_html":"<p>Network meta-analysis has been introduced as an extension of pairwise meta-analysis to facilitate indirect comparisons of multiple interventions that have not been studied in a head-to-head fashion. The use of network meta-analysis is becoming increasingly popular in biomedical sciences, especially in epidemiology and in clinical trials, where the safety and efficacy of a treatment is determined based on a series of studies with similar protocols. A search through medical journals revealed a lack of presentations of Bayesian models within a network meta-analysis framework and thus motivated further research into this combined area of study. The development of four hierarchical Bayesian models applicable to the field of network meta-analysis are presented. Two of them were constructed to estimate all possible drug-group comparisons, whereas the other two concentrate on estimating all pairwise drug comparisons. Moreover, the Bayesian models will also allow borrowing strength from other related studies. Two simulations demonstrating the capabilities of these models are also presented. The first simulation demonstrates the ability of the models to estimate all comparisons. The second simulation focuses on the models' abilities to estimate the overall mean comparison. The models are also applied to data provided in Liu et al.(2012) and the results compared to the bayesian network meta-analysis results presented by Liu et al.(2012).</p>","abstract_has_math":false,"creators":["Waters, Brittany"],"institution":null,"degree_name":"Master of Science in Mathematics (M.S.)","degree_level":"Thesis (restricted to Georgia Southern)","degree_discipline":"Department of Mathematical Sciences","degree_department":null,"school":null,"contributors":["Charles Champ","Broderick Oluyede"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-01-01T08:00:00Z","date_published":"2014-01-01T08:00:00Z","updated_at":"2026-07-24T02:28:00Z","subjects":["ETD","bayesian model","network meta-analysis","Applied Statistics","Statistical Models"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.georgiasouthern.edu/etd/1159","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Charles Champ","Broderick Oluyede"]},{"key":"dc:creator","label":"Author","values":["Waters, Brittany"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2019-07-02T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Mathematical Sciences"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis (restricted to Georgia Southern)"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Mathematics (M.S.)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["ETD","bayesian model","network meta-analysis","Applied Statistics","Statistical Models"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.georgiasouthern.edu/etd/1159"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Network meta-analysis has been introduced as an extension of pairwise meta-analysis to facilitate indirect comparisons of multiple interventions that have not been studied in a head-to-head fashion. The use of network meta-analysis is becoming increasingly popular in biomedical sciences, especially in epidemiology and in clinical trials, where the safety and efficacy of a treatment is determined based on a series of studies with similar protocols. A search through medical journals revealed a lack of presentations of Bayesian models within a network meta-analysis framework and thus motivated further research into this combined area of study. The development of four hierarchical Bayesian models applicable to the field of network meta-analysis are presented. Two of them were constructed to estimate all possible drug-group comparisons, whereas the other two concentrate on estimating all pairwise drug comparisons. Moreover, the Bayesian models will also allow borrowing strength from other related studies. Two simulations demonstrating the capabilities of these models are also presented. The first simulation demonstrates the ability of the models to estimate all comparisons. The second simulation focuses on the models' abilities to estimate the overall mean comparison. The models are also applied to data provided in Liu et al.(2012) and the results compared to the bayesian network meta-analysis results presented by Liu et al.(2012).
"]},{"key":"dc:title","label":"Title","values":["An Applied Bayesian Approach to Network Meta-Analysis"]}]}],"canonical_facts":{"dc:contributor":["Charles Champ","Broderick Oluyede"],"dc:creator":["Waters, Brittany"],"dc:date.available":["2019-07-02T07:00:00Z"],"dc:description.abstract":["Network meta-analysis has been introduced as an extension of pairwise meta-analysis to facilitate indirect comparisons of multiple interventions that have not been studied in a head-to-head fashion. The use of network meta-analysis is becoming increasingly popular in biomedical sciences, especially in epidemiology and in clinical trials, where the safety and efficacy of a treatment is determined based on a series of studies with similar protocols. A search through medical journals revealed a lack of presentations of Bayesian models within a network meta-analysis framework and thus motivated further research into this combined area of study. The development of four hierarchical Bayesian models applicable to the field of network meta-analysis are presented. Two of them were constructed to estimate all possible drug-group comparisons, whereas the other two concentrate on estimating all pairwise drug comparisons. Moreover, the Bayesian models will also allow borrowing strength from other related studies. Two simulations demonstrating the capabilities of these models are also presented. The first simulation demonstrates the ability of the models to estimate all comparisons. The second simulation focuses on the models' abilities to estimate the overall mean comparison. The models are also applied to data provided in Liu et al.(2012) and the results compared to the bayesian network meta-analysis results presented by Liu et al.(2012).
"],"dc:identifier":["https://digitalcommons.georgiasouthern.edu/etd/1159"],"dc:subject":["ETD","bayesian model","network meta-analysis","Applied Statistics","Statistical Models"],"dc:title":["An Applied Bayesian Approach to Network Meta-Analysis"],"thesis:degree_discipline":["Department of Mathematical Sciences"],"thesis:degree_level":["Thesis (restricted to Georgia Southern)"],"thesis:degree_name":["Master of Science in Mathematics (M.S.)"]},"updated_at":"2026-07-24T02:28:00Z"}