{"id":{"repo_id":"vcu","oai_identifier":"oai:scholarscompass.vcu.edu:etd-1376"},"canonical_url":"https://search.dev.ndltd.org/etd/vcu/oai:scholarscompass.vcu.edu:etd-1376","repository":{"repo_id":"vcu","name":"Virginia Commonwealth University","base_url":"https://scholarscompass.vcu.edu/do/oai/"},"display":{"title":"THE EFFECT OF BASELINE CLUSTER STRATIFICATION ON THE POWER OF PRE-POST ANALYSIS","abstract":"The purpose of study is to check whether the power of detecting the effect of intervention versus control in a pre- and post-study can be increased by using a stratified randomized controlled design. A stratified randomized controlled design with two study arms and two time points, where strata are determined by clustering on baseline outcomes of the primary measure, is considered. A modified hierarchical clustering algorithm is developed which guarantees optimality as well as requiring each cluster to have at least one subject per study arm. The power is calculated based on simulated bivariate normal distributed primary measures with mixture normal distributed baseline outcomes. The simulation shows that the power of this approach can be increased compared with using a completely randomized controlled study with no stratification. The difference of the power between with stratification and without stratification increases as the sample size increases or as the correlation of the pre- and post-measures decreases.","abstract_html":"The purpose of study is to check whether the power of detecting the effect of intervention versus control in a pre- and post-study can be increased by using a stratified randomized controlled design. A stratified randomized controlled design with two study arms and two time points, where strata are determined by clustering on baseline outcomes of the primary measure, is considered. A modified hierarchical clustering algorithm is developed which guarantees optimality as well as requiring each cluster to have at least one subject per study arm. The power is calculated based on simulated bivariate normal distributed primary measures with mixture normal distributed baseline outcomes. The simulation shows that the power of this approach can be increased compared with using a completely randomized controlled study with no stratification. The difference of the power between with stratification and without stratification increases as the sample size increases or as the correlation of the pre- and post-measures decreases.","abstract_has_math":false,"creators":["HU, FENGJIAO"],"institution":null,"degree_name":"Master of Science","degree_level":"Thesis","degree_discipline":"Biostatistics","degree_department":null,"school":null,"contributors":["Wen Wan","Robert E. Johnson"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2012,"date_issued":"2012-07-18T07:00:00Z","date_published":"2012-07-18T07:00:00Z","updated_at":"2026-07-24T05:53:56Z","subjects":["Baseline Cluster","Power","Pre-Post Analysis","Biostatistics","Physical Sciences and Mathematics","Statistics and Probability"],"languages":[],"rights":["© The Author"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholarscompass.vcu.edu/etd/377"],"render_values":[{"text":"https://scholarscompass.vcu.edu/etd/377","href":"https://scholarscompass.vcu.edu/etd/377","code":true}]}]},"links":{"outbound_url":"https://doi.org/10.25772/FAM3-EN68","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Wen Wan","Robert E. Johnson"]},{"key":"dc:creator","label":"Author","values":["HU, FENGJIAO"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2017-07-26T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Biostatistics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Baseline Cluster","Power","Pre-Post Analysis","Biostatistics","Physical Sciences and Mathematics","Statistics and Probability"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["© The Author"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://doi.org/10.25772/FAM3-EN68","https://scholarscompass.vcu.edu/etd/377"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The purpose of study is to check whether the power of detecting the effect of intervention versus control in a pre- and post-study can be increased by using a stratified randomized controlled design. A stratified randomized controlled design with two study arms and two time points, where strata are determined by clustering on baseline outcomes of the primary measure, is considered. A modified hierarchical clustering algorithm is developed which guarantees optimality as well as requiring each cluster to have at least one subject per study arm. The power is calculated based on simulated bivariate normal distributed primary measures with mixture normal distributed baseline outcomes. The simulation shows that the power of this approach can be increased compared with using a completely randomized controlled study with no stratification. The difference of the power between with stratification and without stratification increases as the sample size increases or as the correlation of the pre- and post-measures decreases."]},{"key":"dc:title","label":"Title","values":["THE EFFECT OF BASELINE CLUSTER STRATIFICATION ON THE POWER OF PRE-POST ANALYSIS"]}]}],"canonical_facts":{"dc:contributor":["Wen Wan","Robert E. Johnson"],"dc:creator":["HU, FENGJIAO"],"dc:date.available":["2017-07-26T07:00:00Z"],"dc:description.abstract":["The purpose of study is to check whether the power of detecting the effect of intervention versus control in a pre- and post-study can be increased by using a stratified randomized controlled design. A stratified randomized controlled design with two study arms and two time points, where strata are determined by clustering on baseline outcomes of the primary measure, is considered. A modified hierarchical clustering algorithm is developed which guarantees optimality as well as requiring each cluster to have at least one subject per study arm. The power is calculated based on simulated bivariate normal distributed primary measures with mixture normal distributed baseline outcomes. The simulation shows that the power of this approach can be increased compared with using a completely randomized controlled study with no stratification. The difference of the power between with stratification and without stratification increases as the sample size increases or as the correlation of the pre- and post-measures decreases."],"dc:identifier":["https://doi.org/10.25772/FAM3-EN68","https://scholarscompass.vcu.edu/etd/377"],"dc:rights":["© The Author"],"dc:subject":["Baseline Cluster","Power","Pre-Post Analysis","Biostatistics","Physical Sciences and Mathematics","Statistics and Probability"],"dc:title":["THE EFFECT OF BASELINE CLUSTER STRATIFICATION ON THE POWER OF PRE-POST ANALYSIS"],"thesis:degree_discipline":["Biostatistics"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science"]},"updated_at":"2026-07-24T05:53:56Z"}