{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/101713"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/101713","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Causal inference for complex data: randomization inference for treatment effect heterogeneity, network outcomes, and subgroup specific effects","abstract":"This dissertation presents three new methodologies for analyzing randomized controlled trials using the researcher controlled randomization mechanism as the basis for inference. The first method extends inference for the ``attributable effect'', the total of the difference of outcomes if the treatment group had instead been assigned to the control condition, to count and continuous data using a fast approximation algorithm. Alternative approaches are limited to binary data, require asymptotic approximations, or are computationally expensive. A refinement of the method to allow for including additional information is also included. The second method extends randomization inference to the study of network formation. Previous approaches either required strong parametric assumptions or only allowed for pre-treatment networks to be used. This approach develops several test statistics that can be used to test against common network formation models, based purely on the randomization of treatment. The final method improves inference in cluster randomized trials, where collections of individuals are assigned to treatment conditions simultaneously. Under the appealing assumption that larger clusters will have larger outcomes, on average, the method provides efficient, unbiased estimation of average treatment effects requiring minimal additional assumptions. All three of these methods demonstrate the relevance of randomized controlled trials to key areas of science and statistical development as well as the advantages of carefully crafting study design to fit the problem of interest. Data examples include a large scale field experiment involving health insurance, a gene-wide association study involving high dimensional outcomes, and a policy relevant study of parental social capital and student achievement in schools.","abstract_html":"This dissertation presents three new methodologies for analyzing randomized controlled trials using the researcher controlled randomization mechanism as the basis for inference. The first method extends inference for the ``attributable effect'', the total of the difference of outcomes if the treatment group had instead been assigned to the control condition, to count and continuous data using a fast approximation algorithm. Alternative approaches are limited to binary data, require asymptotic approximations, or are computationally expensive. A refinement of the method to allow for including additional information is also included. The second method extends randomization inference to the study of network formation. Previous approaches either required strong parametric assumptions or only allowed for pre-treatment networks to be used. This approach develops several test statistics that can be used to test against common network formation models, based purely on the randomization of treatment. The final method improves inference in cluster randomized trials, where collections of individuals are assigned to treatment conditions simultaneously. Under the appealing assumption that larger clusters will have larger outcomes, on average, the method provides efficient, unbiased estimation of average treatment effects requiring minimal additional assumptions. All three of these methods demonstrate the relevance of randomized controlled trials to key areas of science and statistical development as well as the advantages of carefully crafting study design to fit the problem of interest. Data examples include a large scale field experiment involving health insurance, a gene-wide association study involving high dimensional outcomes, and a policy relevant study of parental social capital and student achievement in schools.","abstract_has_math":false,"creators":["Fredrickson, Mark M."],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Statistics","degree_department":null,"school":null,"contributors":["Chen, Yuguo","Bowers, Jake","Liang, Feng","Hansen, Ben B."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-09-27T16:34:20Z","date_published":"2018-09-27T16:34:20Z","updated_at":"2026-07-22T22:24:40Z","subjects":["Randomized controlled trials, networks, treatment effects, subgroups, inference"],"languages":["en"],"rights":["Copyright 2018 Mark M. Fredrickson"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/101713","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chen, Yuguo","Bowers, Jake","Liang, Feng","Hansen, Ben B."]},{"key":"dc:creator","label":"Author","values":["Fredrickson, Mark M."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-09-27T16:34:20Z","2020-09-28T09:15:13Z","2018-07-12","2018-08"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Statistics"]},{"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":["Randomized controlled trials, networks, treatment effects, subgroups, inference"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2018 Mark M. Fredrickson"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/101713"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This dissertation presents three new methodologies for analyzing randomized controlled trials using the researcher controlled randomization mechanism as the basis for inference. The first method extends inference for the ``attributable effect'', the total of the difference of outcomes if the treatment group had instead been assigned to the control condition, to count and continuous data using a fast approximation algorithm. Alternative approaches are limited to binary data, require asymptotic approximations, or are computationally expensive. A refinement of the method to allow for including additional information is also included. The second method extends randomization inference to the study of network formation. Previous approaches either required strong parametric assumptions or only allowed for pre-treatment networks to be used. This approach develops several test statistics that can be used to test against common network formation models, based purely on the randomization of treatment. The final method improves inference in cluster randomized trials, where collections of individuals are assigned to treatment conditions simultaneously. Under the appealing assumption that larger clusters will have larger outcomes, on average, the method provides efficient, unbiased estimation of average treatment effects requiring minimal additional assumptions. All three of these methods demonstrate the relevance of randomized controlled trials to key areas of science and statistical development as well as the advantages of carefully crafting study design to fit the problem of interest. Data examples include a large scale field experiment involving health insurance, a gene-wide association study involving high dimensional outcomes, and a policy relevant study of parental social capital and student achievement in schools.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-08-01","The student, Mark Fredrickson, accepted the attached license on 2018-07-12 at 16:17.","The student, Mark Fredrickson, submitted this Dissertation for approval on 2018-07-12 at 16:23.","This Dissertation was approved for publication on 2018-07-12 at 17:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12855 on 2018-09-27 at 11:19:17","Made available in DSpace on 2018-09-27T16:34:20Z (GMT). No. of bitstreams: 3 FREDRICKSON-DISSERTATION-2018.pdf: 708329 bytes, checksum: 80d55e82e1b58aefe0df0766a25ece45 (MD5) LICENSE.txt: 4213 bytes, checksum: e4110c6f91e443f6776d692d57a04577 (MD5) PROQUEST_LICENSE.txt: 4559 bytes, checksum: caab6bd74bd877db20908b20ebf9b902 (MD5) Previous issue date: 2018-07-12","Embargo set by: Seth Robbins for item 107813 Lift date: 2020-09-27T16:34:29Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 107813 on 2020-09-28T09:15:13Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Causal inference for complex data: randomization inference for treatment effect heterogeneity, network outcomes, and subgroup specific effects"]}]}],"canonical_facts":{"dc:contributor":["Chen, Yuguo","Bowers, Jake","Liang, Feng","Hansen, Ben B."],"dc:creator":["Fredrickson, Mark M."],"dc:date":["2018-09-27T16:34:20Z","2020-09-28T09:15:13Z","2018-07-12","2018-08"],"dc:description":["This dissertation presents three new methodologies for analyzing randomized controlled trials using the researcher controlled randomization mechanism as the basis for inference. The first method extends inference for the ``attributable effect'', the total of the difference of outcomes if the treatment group had instead been assigned to the control condition, to count and continuous data using a fast approximation algorithm. Alternative approaches are limited to binary data, require asymptotic approximations, or are computationally expensive. A refinement of the method to allow for including additional information is also included. The second method extends randomization inference to the study of network formation. Previous approaches either required strong parametric assumptions or only allowed for pre-treatment networks to be used. This approach develops several test statistics that can be used to test against common network formation models, based purely on the randomization of treatment. The final method improves inference in cluster randomized trials, where collections of individuals are assigned to treatment conditions simultaneously. Under the appealing assumption that larger clusters will have larger outcomes, on average, the method provides efficient, unbiased estimation of average treatment effects requiring minimal additional assumptions. All three of these methods demonstrate the relevance of randomized controlled trials to key areas of science and statistical development as well as the advantages of carefully crafting study design to fit the problem of interest. Data examples include a large scale field experiment involving health insurance, a gene-wide association study involving high dimensional outcomes, and a policy relevant study of parental social capital and student achievement in schools.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-08-01","The student, Mark Fredrickson, accepted the attached license on 2018-07-12 at 16:17.","The student, Mark Fredrickson, submitted this Dissertation for approval on 2018-07-12 at 16:23.","This Dissertation was approved for publication on 2018-07-12 at 17:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12855 on 2018-09-27 at 11:19:17","Made available in DSpace on 2018-09-27T16:34:20Z (GMT). No. of bitstreams: 3 FREDRICKSON-DISSERTATION-2018.pdf: 708329 bytes, checksum: 80d55e82e1b58aefe0df0766a25ece45 (MD5) LICENSE.txt: 4213 bytes, checksum: e4110c6f91e443f6776d692d57a04577 (MD5) PROQUEST_LICENSE.txt: 4559 bytes, checksum: caab6bd74bd877db20908b20ebf9b902 (MD5) Previous issue date: 2018-07-12","Embargo set by: Seth Robbins for item 107813 Lift date: 2020-09-27T16:34:29Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 107813 on 2020-09-28T09:15:13Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/101713"],"dc:language":["en"],"dc:rights":["Copyright 2018 Mark M. Fredrickson"],"dc:subject":["Randomized controlled trials, networks, treatment effects, subgroups, inference"],"dc:title":["Causal inference for complex data: randomization inference for treatment effect heterogeneity, network outcomes, and subgroup specific effects"],"dc:type":["text"],"thesis:degree_discipline":["Statistics"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:40Z"}