{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-11807"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-11807","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"Essays in the Econometrics of Choice Analysis with Applications in Health Economics","abstract":"Unobserved heterogeneity is one of the main concerns for applied economists, particularly when modeling preferences for health and healthcare. Applied economists have preferred the mixed logit model due to its flexible latent structure allowing various specifications of unobserved heterogeneity. Since the model does not have a closed-form, its estimation relies on simulation-based methods, specifically the maximum simulated likelihood (MSL) estimator, which has been the dominant estimation strategy. In the first section of this dissertation, which include chapters 1 through 5, I analyze biases of MSL when applied to the bivariate normal, bivariate Poisson-lognormal and mixed logit models. Discrete choice experiments (DCEs) are often conducted to elicit preferences from individuals on health-related objects. Economists generally assume that given a choice set and a hypothetical scenario, each decision maker selects the alternative that maximizes their decisional utility. In economics, choices are behaviors that imply inequalities in utility (e.g., A > B) that resolve the ambiguities between objects. Although paired comparisons are commonplace in child health valuation, they are highly inefficient and burdensome to respondents: Each choice implies only a single inequality (e.g., A > B), and respondents are forced to choose between two children. In a kaizen task, respondents express their preference for improving a single object in a choice set. Kaizen is a Japanese term that describes continuous improvement, which in this case, is the discrete evolution of an object over a sequence of choices. Kaizen task elicit preference paths (i.e., each respondent’s optimal sequence of improvements from an initial profile toward an idealized destination). In Chapter 6, I present the protocol for kaizen task analysis. The protocol paper was recently published in the BMJ Open. In Chapter 7, I compare the difference between preference elicitation tasks (i.e., paired comparisons and kaizen tasks) and produce an EQ-5D-Y-3L value set for the United States on an “experience” scale instead of the quality-adjusted life years (QALY) scale. Chapter 8 examines the effects of child age and problem duration on US EQ-5D-Y-3L values.","abstract_html":"Unobserved heterogeneity is one of the main concerns for applied economists, particularly when modeling preferences for health and healthcare. Applied economists have preferred the mixed logit model due to its flexible latent structure allowing various specifications of unobserved heterogeneity. Since the model does not have a closed-form, its estimation relies on simulation-based methods, specifically the maximum simulated likelihood (MSL) estimator, which has been the dominant estimation strategy. In the first section of this dissertation, which include chapters 1 through 5, I analyze biases of MSL when applied to the bivariate normal, bivariate Poisson-lognormal and mixed logit models. Discrete choice experiments (DCEs) are often conducted to elicit preferences from individuals on health-related objects. Economists generally assume that given a choice set and a hypothetical scenario, each decision maker selects the alternative that maximizes their decisional utility. In economics, choices are behaviors that imply inequalities in utility (e.g., A &gt; B) that resolve the ambiguities between objects. Although paired comparisons are commonplace in child health valuation, they are highly inefficient and burdensome to respondents: Each choice implies only a single inequality (e.g., A &gt; B), and respondents are forced to choose between two children. In a kaizen task, respondents express their preference for improving a single object in a choice set. Kaizen is a Japanese term that describes continuous improvement, which in this case, is the discrete evolution of an object over a sequence of choices. Kaizen task elicit preference paths (i.e., each respondent’s optimal sequence of improvements from an initial profile toward an idealized destination). In Chapter 6, I present the protocol for kaizen task analysis. The protocol paper was recently published in the BMJ Open. In Chapter 7, I compare the difference between preference elicitation tasks (i.e., paired comparisons and kaizen tasks) and produce an EQ-5D-Y-3L value set for the United States on an “experience” scale instead of the quality-adjusted life years (QALY) scale. Chapter 8 examines the effects of child age and problem duration on US EQ-5D-Y-3L values.","abstract_has_math":false,"creators":["Jumamyradov, Maksat"],"institution":"University of South Florida","degree_name":"Doctor of Philosophy (Ph.D.)","degree_level":"Dissertation","degree_discipline":"Economics","degree_department":null,"school":null,"contributors":["Murat Munkin, Ph.D.","Benjamin M. Craig, Ph.D.","William H. Creene, Ph.D.","Diogo Baerlocher, Ph.D.","Guilia La Mattina, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05-23T07:00:00Z","date_published":"2024-05-23T07:00:00Z","updated_at":"2026-11-19T08:49:48Z","subjects":["mixed logit","maximum simulated likelihood","discrete choice experiment","EQ-5D","quality-adjusted life year","Economics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/10520","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/10520","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-11807","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Murat Munkin, Ph.D.","Benjamin M. Craig, Ph.D.","William H. Creene, Ph.D.","Diogo Baerlocher, Ph.D.","Guilia La Mattina, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Jumamyradov, Maksat"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-05-23T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Economics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation","Ph.D."]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (Ph.D.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["mixed logit","maximum simulated likelihood","discrete choice experiment","EQ-5D","quality-adjusted life year","Economics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/10520"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Unobserved heterogeneity is one of the main concerns for applied economists, particularly when modeling preferences for health and healthcare. Applied economists have preferred the mixed logit model due to its flexible latent structure allowing various specifications of unobserved heterogeneity. Since the model does not have a closed-form, its estimation relies on simulation-based methods, specifically the maximum simulated likelihood (MSL) estimator, which has been the dominant estimation strategy. In the first section of this dissertation, which include chapters 1 through 5, I analyze biases of MSL when applied to the bivariate normal, bivariate Poisson-lognormal and mixed logit models. Discrete choice experiments (DCEs) are often conducted to elicit preferences from individuals on health-related objects. Economists generally assume that given a choice set and a hypothetical scenario, each decision maker selects the alternative that maximizes their decisional utility. In economics, choices are behaviors that imply inequalities in utility (e.g., A > B) that resolve the ambiguities between objects. Although paired comparisons are commonplace in child health valuation, they are highly inefficient and burdensome to respondents: Each choice implies only a single inequality (e.g., A > B), and respondents are forced to choose between two children. In a kaizen task, respondents express their preference for improving a single object in a choice set. Kaizen is a Japanese term that describes continuous improvement, which in this case, is the discrete evolution of an object over a sequence of choices. Kaizen task elicit preference paths (i.e., each respondent’s optimal sequence of improvements from an initial profile toward an idealized destination). In Chapter 6, I present the protocol for kaizen task analysis. The protocol paper was recently published in the BMJ Open. In Chapter 7, I compare the difference between preference elicitation tasks (i.e., paired comparisons and kaizen tasks) and produce an EQ-5D-Y-3L value set for the United States on an “experience” scale instead of the quality-adjusted life years (QALY) scale. Chapter 8 examines the effects of child age and problem duration on US EQ-5D-Y-3L values."]},{"key":"dc:title","label":"Title","values":["Essays in the Econometrics of Choice Analysis with Applications in Health Economics"]}]}],"canonical_facts":{"dc:contributor":["Murat Munkin, Ph.D.","Benjamin M. Craig, Ph.D.","William H. Creene, Ph.D.","Diogo Baerlocher, Ph.D.","Guilia La Mattina, Ph.D."],"dc:creator":["Jumamyradov, Maksat"],"dc:date":["2024-05-23T07:00:00Z"],"dc:description":["Unobserved heterogeneity is one of the main concerns for applied economists, particularly when modeling preferences for health and healthcare. Applied economists have preferred the mixed logit model due to its flexible latent structure allowing various specifications of unobserved heterogeneity. Since the model does not have a closed-form, its estimation relies on simulation-based methods, specifically the maximum simulated likelihood (MSL) estimator, which has been the dominant estimation strategy. In the first section of this dissertation, which include chapters 1 through 5, I analyze biases of MSL when applied to the bivariate normal, bivariate Poisson-lognormal and mixed logit models. Discrete choice experiments (DCEs) are often conducted to elicit preferences from individuals on health-related objects. Economists generally assume that given a choice set and a hypothetical scenario, each decision maker selects the alternative that maximizes their decisional utility. In economics, choices are behaviors that imply inequalities in utility (e.g., A > B) that resolve the ambiguities between objects. Although paired comparisons are commonplace in child health valuation, they are highly inefficient and burdensome to respondents: Each choice implies only a single inequality (e.g., A > B), and respondents are forced to choose between two children. In a kaizen task, respondents express their preference for improving a single object in a choice set. Kaizen is a Japanese term that describes continuous improvement, which in this case, is the discrete evolution of an object over a sequence of choices. Kaizen task elicit preference paths (i.e., each respondent’s optimal sequence of improvements from an initial profile toward an idealized destination). In Chapter 6, I present the protocol for kaizen task analysis. The protocol paper was recently published in the BMJ Open. In Chapter 7, I compare the difference between preference elicitation tasks (i.e., paired comparisons and kaizen tasks) and produce an EQ-5D-Y-3L value set for the United States on an “experience” scale instead of the quality-adjusted life years (QALY) scale. Chapter 8 examines the effects of child age and problem duration on US EQ-5D-Y-3L values."],"dc:identifier":["https://digitalcommons.usf.edu/etd/10520"],"dc:subject":["mixed logit","maximum simulated likelihood","discrete choice experiment","EQ-5D","quality-adjusted life year","Economics"],"dc:title":["Essays in the Econometrics of Choice Analysis with Applications in Health Economics"],"thesis:degree_discipline":["Economics"],"thesis:degree_level":["Dissertation","Ph.D."],"thesis:degree_name":["Doctor of Philosophy (Ph.D.)"],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:49:48Z"}