{"id":{"repo_id":"duquesne","oai_identifier":"oai:dsc.duq.edu:etd-1364"},"canonical_url":"https://search.dev.ndltd.org/etd/duquesne/oai:dsc.duq.edu:etd-1364","repository":{"repo_id":"duquesne","name":"Duquesne","base_url":"https://dsc.duq.edu/do/oai/"},"display":{"title":"Neural Network Prediction of Math and Reading Proficiency as Reported in the Educational Longitudinal Study 2002 Based on Non-Curricular Variables","abstract":"Predicting student achievement is often the goal of many studies, and a frequently employed tool for constructing predictive models is multiple linear regression. This research sought to compare the performance of a three-layer back propagation neural network to that of traditional multiple linear regression in predicting math and reading proficiency from 103 non-curricular variables collected in the National Center for Educational Statistics' 2002 Educational Longitudinal Study. The neural network model was implemented using the Java programming language and the coefficients for the regression equations were produced by SPSS. The results showed that, for this data set, neither model provided an advantage over the other in terms prediction accuracy when presented with error-free cases. When synthetic noise was introduced into the data, however, the neural network model showed a greater resistance to degradation. The fact that the neural network model performed as well as, and in some cases better than, regression suggests that further study of neural network modeling is warranted to better understand the most effective ways to harness this flexible modeling technology.","abstract_html":"Predicting student achievement is often the goal of many studies, and a frequently employed tool for constructing predictive models is multiple linear regression. This research sought to compare the performance of a three-layer back propagation neural network to that of traditional multiple linear regression in predicting math and reading proficiency from 103 non-curricular variables collected in the National Center for Educational Statistics' 2002 Educational Longitudinal Study. The neural network model was implemented using the Java programming language and the coefficients for the regression equations were produced by SPSS. The results showed that, for this data set, neither model provided an advantage over the other in terms prediction accuracy when presented with error-free cases. When synthetic noise was introduced into the data, however, the neural network model showed a greater resistance to degradation. The fact that the neural network model performed as well as, and in some cases better than, regression suggests that further study of neural network modeling is warranted to better understand the most effective ways to harness this flexible modeling technology.","abstract_has_math":false,"creators":["Brown, Jason"],"institution":null,"degree_name":"EdD","degree_level":"Immediate Access","degree_discipline":"Instructional Technology (EdDIT)","degree_department":null,"school":null,"contributors":["Connie M. Moss","Misook Heo","Susan Brookhart"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2007,"date_issued":"2007-01-01T08:00:00Z","date_published":"2007-01-01T08:00:00Z","updated_at":"2026-07-24T02:09:20Z","subjects":["back propagation","linear regression","neural network","prediction","student achievement"],"languages":["English"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://dsc.duq.edu/etd/351","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Connie M. Moss","Misook Heo","Susan Brookhart"]},{"key":"dc:creator","label":"Author","values":["Brown, Jason"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2018-08-03T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Instructional Technology (EdDIT)"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Immediate Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["EdD"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["back propagation","linear regression","neural network","prediction","student achievement"]}]},{"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":["https://dsc.duq.edu/etd/351"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Predicting student achievement is often the goal of many studies, and a frequently employed tool for constructing predictive models is multiple linear regression. This research sought to compare the performance of a three-layer back propagation neural network to that of traditional multiple linear regression in predicting math and reading proficiency from 103 non-curricular variables collected in the National Center for Educational Statistics' 2002 Educational Longitudinal Study. The neural network model was implemented using the Java programming language and the coefficients for the regression equations were produced by SPSS. The results showed that, for this data set, neither model provided an advantage over the other in terms prediction accuracy when presented with error-free cases. When synthetic noise was introduced into the data, however, the neural network model showed a greater resistance to degradation. The fact that the neural network model performed as well as, and in some cases better than, regression suggests that further study of neural network modeling is warranted to better understand the most effective ways to harness this flexible modeling technology."]},{"key":"dc:title","label":"Title","values":["Neural Network Prediction of Math and Reading Proficiency as Reported in the Educational Longitudinal Study 2002 Based on Non-Curricular Variables"]}]}],"canonical_facts":{"dc:contributor":["Connie M. Moss","Misook Heo","Susan Brookhart"],"dc:creator":["Brown, Jason"],"dc:date.available":["2018-08-03T07:00:00Z"],"dc:description.abstract":["Predicting student achievement is often the goal of many studies, and a frequently employed tool for constructing predictive models is multiple linear regression. This research sought to compare the performance of a three-layer back propagation neural network to that of traditional multiple linear regression in predicting math and reading proficiency from 103 non-curricular variables collected in the National Center for Educational Statistics' 2002 Educational Longitudinal Study. The neural network model was implemented using the Java programming language and the coefficients for the regression equations were produced by SPSS. The results showed that, for this data set, neither model provided an advantage over the other in terms prediction accuracy when presented with error-free cases. When synthetic noise was introduced into the data, however, the neural network model showed a greater resistance to degradation. The fact that the neural network model performed as well as, and in some cases better than, regression suggests that further study of neural network modeling is warranted to better understand the most effective ways to harness this flexible modeling technology."],"dc:identifier":["https://dsc.duq.edu/etd/351"],"dc:language":["English"],"dc:subject":["back propagation","linear regression","neural network","prediction","student achievement"],"dc:title":["Neural Network Prediction of Math and Reading Proficiency as Reported in the Educational Longitudinal Study 2002 Based on Non-Curricular Variables"],"thesis:degree_discipline":["Instructional Technology (EdDIT)"],"thesis:degree_level":["Immediate Access"],"thesis:degree_name":["EdD"]},"updated_at":"2026-07-24T02:09:20Z"}