{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/18452"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/18452","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"The effectiveness of using multiple item pools to increase test security in computerized adaptive testing","abstract":"The purpose of this study is to investigate the effectiveness of a multiple item pool design verse the commonly used single pool design in terms of measurement precision, item exposure control and item pool usage balance for Computerized Adaptive Testing (CAT). Also, the extent to that multiple item pools can reduce the bias of CAT in the presence of possibly compromised items will be explored. Item selection algorithms were designed using three conditions: item pool configuration (single item pool, two item pools, and three item pools), item selection method (the random item selection method, the maximum information item selection method, and the a-Stratified item selection method), and four different item exposure control parameters from the Sympson-Hettter method. To investigate the effect of possibly compromised items and multiple item pools on measurement precision, compromised items were defined as overexposed items, thus becoming artificially compromised items for this study. They were then treated as known to all examinees, to represent the worst case scenario. These possibly compromised items were assigned to two different locations: (a) both unique and common item pools, and (b) unique item pools only. The simulation studies were conducted with two different item bank sizes (N=420 from the NAEP math assessment item parameters, and N=720 from generated form distribution), and various numbers of simulated examines from N (0,1). The results of this study indicated that when there were no artificially compromised items in the item bank, the multiple item pool design maintained measurement precision, and multiple item pools outperformed a single pool in terms of item exposure control and item pool usage. Once artificially compromised items were introduced to the item pools, the allocation of the artificially compromised items to unique item pools only (as compared to allocation to both common and unique item pools) helped improve measurement precision.","abstract_html":"The purpose of this study is to investigate the effectiveness of a multiple item pool design verse the commonly used single pool design in terms of measurement precision, item exposure control and item pool usage balance for Computerized Adaptive Testing (CAT). Also, the extent to that multiple item pools can reduce the bias of CAT in the presence of possibly compromised items will be explored. Item selection algorithms were designed using three conditions: item pool configuration (single item pool, two item pools, and three item pools), item selection method (the random item selection method, the maximum information item selection method, and the a-Stratified item selection method), and four different item exposure control parameters from the Sympson-Hettter method. To investigate the effect of possibly compromised items and multiple item pools on measurement precision, compromised items were defined as overexposed items, thus becoming artificially compromised items for this study. They were then treated as known to all examinees, to represent the worst case scenario. These possibly compromised items were assigned to two different locations: (a) both unique and common item pools, and (b) unique item pools only. The simulation studies were conducted with two different item bank sizes (N=420 from the NAEP math assessment item parameters, and N=720 from generated form distribution), and various numbers of simulated examines from N (0,1). The results of this study indicated that when there were no artificially compromised items in the item bank, the multiple item pool design maintained measurement precision, and multiple item pools outperformed a single pool in terms of item exposure control and item pool usage. Once artificially compromised items were introduced to the item pools, the allocation of the artificially compromised items to unique item pools only (as compared to allocation to both common and unique item pools) helped improve measurement precision.","abstract_has_math":false,"creators":["Lim, Eun Young"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Educational Psychology","degree_department":null,"school":null,"contributors":["Chang, Hua-Hua","Anderson, Carolyn J.","Douglas, Jeffrey A.","Zhang, Jinming","Roussos, Louis A."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2011,"date_issued":"2011-01-14T22:51:21Z","date_published":"2011-01-14T22:51:21Z","updated_at":"2026-07-22T22:25:11Z","subjects":["Computerized Adaptive Testing","Multiple Item Pools","Test Security"],"languages":["en"],"rights":["Copyright 2010 Eun Young Lim"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/18452","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chang, Hua-Hua","Anderson, Carolyn J.","Douglas, Jeffrey A.","Zhang, Jinming","Roussos, Louis A."]},{"key":"dc:creator","label":"Author","values":["Lim, Eun Young"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2011-01-14T22:51:21Z","2013-02-09T11:00:20Z","2010-12"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Educational 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":["Computerized Adaptive Testing","Multiple Item Pools","Test Security"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2010 Eun Young Lim"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/18452"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The purpose of this study is to investigate the effectiveness of a multiple item pool design verse the commonly used single pool design in terms of measurement precision, item exposure control and item pool usage balance for Computerized Adaptive Testing (CAT). Also, the extent to that multiple item pools can reduce the bias of CAT in the presence of possibly compromised items will be explored. Item selection algorithms were designed using three conditions: item pool configuration (single item pool, two item pools, and three item pools), item selection method (the random item selection method, the maximum information item selection method, and the a-Stratified item selection method), and four different item exposure control parameters from the Sympson-Hettter method. To investigate the effect of possibly compromised items and multiple item pools on measurement precision, compromised items were defined as overexposed items, thus becoming artificially compromised items for this study. They were then treated as known to all examinees, to represent the worst case scenario. These possibly compromised items were assigned to two different locations: (a) both unique and common item pools, and (b) unique item pools only. The simulation studies were conducted with two different item bank sizes (N=420 from the NAEP math assessment item parameters, and N=720 from generated form distribution), and various numbers of simulated examines from N (0,1). The results of this study indicated that when there were no artificially compromised items in the item bank, the multiple item pool design maintained measurement precision, and multiple item pools outperformed a single pool in terms of item exposure control and item pool usage. Once artificially compromised items were introduced to the item pools, the allocation of the artificially compromised items to unique item pools only (as compared to allocation to both common and unique item pools) helped improve measurement precision.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2010-08-12T13:35:58Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Lim_EunYoung_final.pdf: 1506394 bytes, checksum: f5a7b8d60d06546b4df8ffbfc9b72639 (MD5)","Made available in DSpace on 2011-01-14T22:51:21Z (GMT). No. of bitstreams: 2 Lim_EunYoung.pdf: 1506423 bytes, checksum: 34d60075cd83cd2435694e8f88f24603 (MD5) license.txt: 4056 bytes, checksum: f23d59aa12baab0c84cf634638f68497 (MD5)","Item marked as restricted to the 'UIUC Users [automated]' Group (id=2) by Sarah Shreeves (sshreeve@illinois.edu) on 2011-02-08T21:54:31Z Item is restricted until 2013-02-08T21:54:31Z","Item reinstated by Sarah Shreeves (sshreeve@illinois.edu) on 2013-02-09T11:00:19Z Item was in collections: University of Illinois Dissertations and Theses (ID: 204) College of Education Dissertations and Theses (ID: 434) No. of bitstreams: 2 Lim_EunYoung.pdf: 1506423 bytes, checksum: 34d60075cd83cd2435694e8f88f24603 (MD5) license.txt: 4056 bytes, checksum: f23d59aa12baab0c84cf634638f68497 (MD5)","Item released from any restrictions by Sarah Shreeves (sshreeve@illinois.edu) on 2013-02-09T11:00:20Z"]},{"key":"dc:title","label":"Title","values":["The effectiveness of using multiple item pools to increase test security in computerized adaptive testing"]}]}],"canonical_facts":{"dc:contributor":["Chang, Hua-Hua","Anderson, Carolyn J.","Douglas, Jeffrey A.","Zhang, Jinming","Roussos, Louis A."],"dc:creator":["Lim, Eun Young"],"dc:date":["2011-01-14T22:51:21Z","2013-02-09T11:00:20Z","2010-12"],"dc:description":["The purpose of this study is to investigate the effectiveness of a multiple item pool design verse the commonly used single pool design in terms of measurement precision, item exposure control and item pool usage balance for Computerized Adaptive Testing (CAT). Also, the extent to that multiple item pools can reduce the bias of CAT in the presence of possibly compromised items will be explored. Item selection algorithms were designed using three conditions: item pool configuration (single item pool, two item pools, and three item pools), item selection method (the random item selection method, the maximum information item selection method, and the a-Stratified item selection method), and four different item exposure control parameters from the Sympson-Hettter method. To investigate the effect of possibly compromised items and multiple item pools on measurement precision, compromised items were defined as overexposed items, thus becoming artificially compromised items for this study. They were then treated as known to all examinees, to represent the worst case scenario. These possibly compromised items were assigned to two different locations: (a) both unique and common item pools, and (b) unique item pools only. The simulation studies were conducted with two different item bank sizes (N=420 from the NAEP math assessment item parameters, and N=720 from generated form distribution), and various numbers of simulated examines from N (0,1). The results of this study indicated that when there were no artificially compromised items in the item bank, the multiple item pool design maintained measurement precision, and multiple item pools outperformed a single pool in terms of item exposure control and item pool usage. Once artificially compromised items were introduced to the item pools, the allocation of the artificially compromised items to unique item pools only (as compared to allocation to both common and unique item pools) helped improve measurement precision.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2010-08-12T13:35:58Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Lim_EunYoung_final.pdf: 1506394 bytes, checksum: f5a7b8d60d06546b4df8ffbfc9b72639 (MD5)","Made available in DSpace on 2011-01-14T22:51:21Z (GMT). No. of bitstreams: 2 Lim_EunYoung.pdf: 1506423 bytes, checksum: 34d60075cd83cd2435694e8f88f24603 (MD5) license.txt: 4056 bytes, checksum: f23d59aa12baab0c84cf634638f68497 (MD5)","Item marked as restricted to the 'UIUC Users [automated]' Group (id=2) by Sarah Shreeves (sshreeve@illinois.edu) on 2011-02-08T21:54:31Z Item is restricted until 2013-02-08T21:54:31Z","Item reinstated by Sarah Shreeves (sshreeve@illinois.edu) on 2013-02-09T11:00:19Z Item was in collections: University of Illinois Dissertations and Theses (ID: 204) College of Education Dissertations and Theses (ID: 434) No. of bitstreams: 2 Lim_EunYoung.pdf: 1506423 bytes, checksum: 34d60075cd83cd2435694e8f88f24603 (MD5) license.txt: 4056 bytes, checksum: f23d59aa12baab0c84cf634638f68497 (MD5)","Item released from any restrictions by Sarah Shreeves (sshreeve@illinois.edu) on 2013-02-09T11:00:20Z"],"dc:identifier":["http://hdl.handle.net/2142/18452"],"dc:language":["en"],"dc:rights":["Copyright 2010 Eun Young Lim"],"dc:subject":["Computerized Adaptive Testing","Multiple Item Pools","Test Security"],"dc:title":["The effectiveness of using multiple item pools to increase test security in computerized adaptive testing"],"thesis:degree_discipline":["Educational Psychology"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:11Z"}