{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/69694"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/69694","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Identification of Best Modeled Test Items","abstract":"Latent trait models have tremendous power for solving practical measurement problems. This power is realized, however, only when the models adequately characterize observations. Accordingly, a large number of procedures have been proposed to evaluate model goodness of fit. None of these procedures, though, is entirely satisfactory. Some are theoretically or methodologically flawed, others are limited in power or scope. A new approach to the question of model fit was therefore developed. This approach differs from existing procedures in several respects, and thus avoids many common pitfalls. For example, while most available methods are designed to recognize misspecified item response functions, test multidimensionality, or unmodeled dependencies among items, the new approach is designed to be sensitive to all of these. Further, whereas most methods attempt to identify and eliminate poorly modeled items, the new approach attempts to discover subsets of items that are well modeled. The advantage is that while available methods will eventually reject every item as sample size increases, the well modeled subset identified by the new approach should remain relatively invariant.","abstract_html":"Latent trait models have tremendous power for solving practical measurement problems. This power is realized, however, only when the models adequately characterize observations. Accordingly, a large number of procedures have been proposed to evaluate model goodness of fit. None of these procedures, though, is entirely satisfactory. Some are theoretically or methodologically flawed, others are limited in power or scope. A new approach to the question of model fit was therefore developed. This approach differs from existing procedures in several respects, and thus avoids many common pitfalls. For example, while most available methods are designed to recognize misspecified item response functions, test multidimensionality, or unmodeled dependencies among items, the new approach is designed to be sensitive to all of these. Further, whereas most methods attempt to identify and eliminate poorly modeled items, the new approach attempts to discover subsets of items that are well modeled. The advantage is that while available methods will eventually reject every item as sample size increases, the well modeled subset identified by the new approach should remain relatively invariant.","abstract_has_math":false,"creators":["Davey, Timothy C."],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Psychology","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-12-15T19:46:21Z","date_published":"2014-12-15T19:46:21Z","updated_at":"2026-07-22T22:26:01Z","subjects":["Psychology, Psychometrics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["(UMI)AAI8803014"],"render_values":[{"text":"(UMI)AAI8803014","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/2142/69694","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Davey, Timothy C."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2014-12-15T19:46:21Z","10000-01-01","1987"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Psychology"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Psychology, Psychometrics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/69694","(UMI)AAI8803014"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Latent trait models have tremendous power for solving practical measurement problems. This power is realized, however, only when the models adequately characterize observations. Accordingly, a large number of procedures have been proposed to evaluate model goodness of fit. None of these procedures, though, is entirely satisfactory. Some are theoretically or methodologically flawed, others are limited in power or scope. A new approach to the question of model fit was therefore developed. This approach differs from existing procedures in several respects, and thus avoids many common pitfalls. For example, while most available methods are designed to recognize misspecified item response functions, test multidimensionality, or unmodeled dependencies among items, the new approach is designed to be sensitive to all of these. Further, whereas most methods attempt to identify and eliminate poorly modeled items, the new approach attempts to discover subsets of items that are well modeled. The advantage is that while available methods will eventually reject every item as sample size increases, the well modeled subset identified by the new approach should remain relatively invariant.","The performance of this new procedure was assessed through its application to both simulated and real data sets. A high level of sensitivity to a variety of modeling errors was demonstrated.","Made available in DSpace on 2014-12-15T19:46:21Z (GMT). No. of bitstreams: 1 8803014.pdf: 3579445 bytes, checksum: 6bddaa017f84fb7b018b2c42323939ea (MD5) Previous issue date: 1987","Embargo set by: Seth Robbins for item 69860 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","109 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1987."]},{"key":"dc:title","label":"Title","values":["Identification of Best Modeled Test Items"]}]}],"canonical_facts":{"dc:creator":["Davey, Timothy C."],"dc:date":["2014-12-15T19:46:21Z","10000-01-01","1987"],"dc:description":["Latent trait models have tremendous power for solving practical measurement problems. This power is realized, however, only when the models adequately characterize observations. Accordingly, a large number of procedures have been proposed to evaluate model goodness of fit. None of these procedures, though, is entirely satisfactory. Some are theoretically or methodologically flawed, others are limited in power or scope. A new approach to the question of model fit was therefore developed. This approach differs from existing procedures in several respects, and thus avoids many common pitfalls. For example, while most available methods are designed to recognize misspecified item response functions, test multidimensionality, or unmodeled dependencies among items, the new approach is designed to be sensitive to all of these. Further, whereas most methods attempt to identify and eliminate poorly modeled items, the new approach attempts to discover subsets of items that are well modeled. The advantage is that while available methods will eventually reject every item as sample size increases, the well modeled subset identified by the new approach should remain relatively invariant.","The performance of this new procedure was assessed through its application to both simulated and real data sets. A high level of sensitivity to a variety of modeling errors was demonstrated.","Made available in DSpace on 2014-12-15T19:46:21Z (GMT). No. of bitstreams: 1 8803014.pdf: 3579445 bytes, checksum: 6bddaa017f84fb7b018b2c42323939ea (MD5) Previous issue date: 1987","Embargo set by: Seth Robbins for item 69860 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","109 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1987."],"dc:identifier":["http://hdl.handle.net/2142/69694","(UMI)AAI8803014"],"dc:subject":["Psychology, Psychometrics"],"dc:title":["Identification of Best Modeled Test Items"],"dc:type":["text"],"thesis:degree_discipline":["Psychology"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:01Z"}