The current study employed a Monte Carlo design to examine whether samplebased and formula-based estimates of cross-validated R2 differ in accuracy when predictor selection is and is not performed. Analyses were conducted on three datasets with 5, 10, or 15 predictors and different predictor-criterion relationships. Results demonstrated that, in most cases, a formula-based estimate of the cross-validated R2 was as accurate as a sample-based estimate. The one exception was the five predictor case wherein the formula-based estimate exhibited substantially greater bias than the estimate from a sample-based cross validation study. Thus, formula-based estimates, which have an enormous practical advantage over a two sample cross validation study, can be used in most cases without fear of greater error.
","abstract_html":"<p>The current study employed a Monte Carlo design to examine whether samplebased and formula-based estimates of cross-validated R2 differ in accuracy when predictor selection is and is not performed. Analyses were conducted on three datasets with 5, 10, or 15 predictors and different predictor-criterion relationships. Results demonstrated that, in most cases, a formula-based estimate of the cross-validated R2 was as accurate as a sample-based estimate. The one exception was the five predictor case wherein the formula-based estimate exhibited substantially greater bias than the estimate from a sample-based cross validation study. Thus, formula-based estimates, which have an enormous practical advantage over a two sample cross validation study, can be used in most cases without fear of greater error.</p>","abstract_has_math":false,"creators":["Kircher, Andrew J."],"institution":null,"degree_name":"Master of Science","degree_level":null,"degree_discipline":"Department of Psychological Sciences","degree_department":null,"school":null,"contributors":["Reagan D. Brown (Director), Elizabeth L. Shoenfelt, Amber N. Schroeder"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-05-01T07:00:00Z","date_published":"2015-05-01T07:00:00Z","updated_at":"2026-07-24T06:08:52Z","subjects":["Predictor","Criterion","Formula","Based","Applied Behavior Analysis","Psychology"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.wku.edu/theses/1472","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Reagan D. Brown (Director), Elizabeth L. Shoenfelt, Amber N. Schroeder"]},{"key":"dc:creator","label":"Author","values":["Kircher, Andrew J."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Psychological Sciences"]},{"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":["Predictor","Criterion","Formula","Based","Applied Behavior Analysis","Psychology"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.wku.edu/theses/1472"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The current study employed a Monte Carlo design to examine whether samplebased and formula-based estimates of cross-validated R2 differ in accuracy when predictor selection is and is not performed. Analyses were conducted on three datasets with 5, 10, or 15 predictors and different predictor-criterion relationships. Results demonstrated that, in most cases, a formula-based estimate of the cross-validated R2 was as accurate as a sample-based estimate. The one exception was the five predictor case wherein the formula-based estimate exhibited substantially greater bias than the estimate from a sample-based cross validation study. Thus, formula-based estimates, which have an enormous practical advantage over a two sample cross validation study, can be used in most cases without fear of greater error.
"]},{"key":"dc:title","label":"Title","values":["Estimation of the Squared Population Cross-Validity Under Conditions of Predictor Selection"]}]}],"canonical_facts":{"dc:contributor":["Reagan D. Brown (Director), Elizabeth L. Shoenfelt, Amber N. Schroeder"],"dc:creator":["Kircher, Andrew J."],"dc:description.abstract":["The current study employed a Monte Carlo design to examine whether samplebased and formula-based estimates of cross-validated R2 differ in accuracy when predictor selection is and is not performed. Analyses were conducted on three datasets with 5, 10, or 15 predictors and different predictor-criterion relationships. Results demonstrated that, in most cases, a formula-based estimate of the cross-validated R2 was as accurate as a sample-based estimate. The one exception was the five predictor case wherein the formula-based estimate exhibited substantially greater bias than the estimate from a sample-based cross validation study. Thus, formula-based estimates, which have an enormous practical advantage over a two sample cross validation study, can be used in most cases without fear of greater error.
"],"dc:identifier":["https://digitalcommons.wku.edu/theses/1472"],"dc:subject":["Predictor","Criterion","Formula","Based","Applied Behavior Analysis","Psychology"],"dc:title":["Estimation of the Squared Population Cross-Validity Under Conditions of Predictor Selection"],"dc:type":["Thesis"],"thesis:degree_discipline":["Department of Psychological Sciences"],"thesis:degree_name":["Master of Science"]},"updated_at":"2026-07-24T06:08:52Z"}