{"id":{"repo_id":"unt","oai_identifier":"info:ark/67531/metadc4242"},"canonical_url":"https://search.dev.ndltd.org/etd/unt/info:ark/67531/metadc4242","repository":{"repo_id":"unt","name":"University of North Texas","base_url":"https://digital.library.unt.edu/oai/"},"display":{"title":"Comparisons of Improvement-Over-Chance Effect Sizes for Two Groups Under Variance Heterogeneity and Prior Probabilities","abstract":"The distributional properties of improvement-over-chance, I, effect sizes derived from linear and quadratic predictive discriminant analysis (PDA) and from logistic regression analysis (LRA) for the two-group univariate classification were examined. Data were generated under varying levels of four data conditions: population separation, variance pattern, sample size, and prior probabilities. None of the indices provided acceptable estimates of effect for all the conditions examined. There were only a small number of conditions under which both accuracy and precision were acceptable. The results indicate that the decision of which method to choose is primarily determined by variance pattern and prior probabilities. Under variance homogeneity, any of the methods may be recommended. However, LRA is recommended when priors are equal or extreme and linear PDA is recommended when priors are moderate. Under variance heterogeneity, selecting a recommended method is more complex. In many cases, more than one method could be used appropriately.","abstract_html":"The distributional properties of improvement-over-chance, I, effect sizes derived from linear and quadratic predictive discriminant analysis (PDA) and from logistic regression analysis (LRA) for the two-group univariate classification were examined. Data were generated under varying levels of four data conditions: population separation, variance pattern, sample size, and prior probabilities. None of the indices provided acceptable estimates of effect for all the conditions examined. There were only a small number of conditions under which both accuracy and precision were acceptable. The results indicate that the decision of which method to choose is primarily determined by variance pattern and prior probabilities. Under variance homogeneity, any of the methods may be recommended. However, LRA is recommended when priors are equal or extreme and linear PDA is recommended when priors are moderate. Under variance heterogeneity, selecting a recommended method is more complex. In many cases, more than one method could be used appropriately.","abstract_has_math":false,"creators":["Alexander, Erika D."],"institution":"University of North Texas","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Henson, Robin K.","Young, Jon I.","Schumacker, Randall E."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2003,"date_issued":"2003-05","date_published":"2003-05","updated_at":"2026-07-24T05:35:09Z","subjects":["Discriminant analysis.","Logistic regression analysis.","prior probabilities","effect sizes","predictive discriminant analysis","logistic regression","simulation"],"languages":["English"],"rights":["Public","Copyright","Alexander, Erika D.","Copyright is held by the author, unless otherwise noted. All rights reserved."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["oclc: 53153177","https://digital.library.unt.edu/ark:/67531/metadc4242/","ark: ark:/67531/metadc4242"],"render_values":[{"text":"oclc: 53153177","href":null,"code":true},{"text":"https://digital.library.unt.edu/ark:/67531/metadc4242/","href":"https://digital.library.unt.edu/ark:/67531/metadc4242/","code":true},{"text":"ark: ark:/67531/metadc4242","href":null,"code":true}]}]},"links":{"outbound_url":"https://doi.org/10.12794/metadc4242","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Henson, Robin K.","Young, Jon I.","Schumacker, Randall E."]},{"key":"dc:creator","label":"Author","values":["Alexander, Erika D."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2003-05"]},{"key":"dc:publisher","label":"Institution","values":["University of North Texas"]},{"key":"dc:type","label":"Dc Type","values":["Thesis or Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Discriminant analysis.","Logistic regression analysis.","prior probabilities","effect sizes","predictive discriminant analysis","logistic regression","simulation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:rights","label":"Dc Rights","values":["Public","Copyright","Alexander, Erika D.","Copyright is held by the author, unless otherwise noted. All rights reserved."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["oclc: 53153177","doi: 10.12794/metadc4242","https://digital.library.unt.edu/ark:/67531/metadc4242/","ark: ark:/67531/metadc4242"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The distributional properties of improvement-over-chance, I, effect sizes derived from linear and quadratic predictive discriminant analysis (PDA) and from logistic regression analysis (LRA) for the two-group univariate classification were examined. Data were generated under varying levels of four data conditions: population separation, variance pattern, sample size, and prior probabilities. None of the indices provided acceptable estimates of effect for all the conditions examined. There were only a small number of conditions under which both accuracy and precision were acceptable. The results indicate that the decision of which method to choose is primarily determined by variance pattern and prior probabilities. Under variance homogeneity, any of the methods may be recommended. However, LRA is recommended when priors are equal or extreme and linear PDA is recommended when priors are moderate. Under variance heterogeneity, selecting a recommended method is more complex. In many cases, more than one method could be used appropriately."]},{"key":"dc:format","label":"Dc Format","values":["Text"]},{"key":"dc:title","label":"Title","values":["Comparisons of Improvement-Over-Chance Effect Sizes for Two Groups Under Variance Heterogeneity and Prior Probabilities"]}]}],"canonical_facts":{"dc:contributor":["Henson, Robin K.","Young, Jon I.","Schumacker, Randall E."],"dc:creator":["Alexander, Erika D."],"dc:date":["2003-05"],"dc:description":["The distributional properties of improvement-over-chance, I, effect sizes derived from linear and quadratic predictive discriminant analysis (PDA) and from logistic regression analysis (LRA) for the two-group univariate classification were examined. Data were generated under varying levels of four data conditions: population separation, variance pattern, sample size, and prior probabilities. None of the indices provided acceptable estimates of effect for all the conditions examined. There were only a small number of conditions under which both accuracy and precision were acceptable. The results indicate that the decision of which method to choose is primarily determined by variance pattern and prior probabilities. Under variance homogeneity, any of the methods may be recommended. However, LRA is recommended when priors are equal or extreme and linear PDA is recommended when priors are moderate. Under variance heterogeneity, selecting a recommended method is more complex. In many cases, more than one method could be used appropriately."],"dc:format":["Text"],"dc:identifier":["oclc: 53153177","doi: 10.12794/metadc4242","https://digital.library.unt.edu/ark:/67531/metadc4242/","ark: ark:/67531/metadc4242"],"dc:language":["English"],"dc:publisher":["University of North Texas"],"dc:rights":["Public","Copyright","Alexander, Erika D.","Copyright is held by the author, unless otherwise noted. All rights reserved."],"dc:subject":["Discriminant analysis.","Logistic regression analysis.","prior probabilities","effect sizes","predictive discriminant analysis","logistic regression","simulation"],"dc:title":["Comparisons of Improvement-Over-Chance Effect Sizes for Two Groups Under Variance Heterogeneity and Prior Probabilities"],"dc:type":["Thesis or Dissertation"]},"updated_at":"2026-07-24T05:35:09Z"}