This dissertation examines data collected from Kentucky Drug Court to determine factors associated with program completion outcomes. Extant research on drug court completion outcomes is generally limited to individual drug courts and includes small numbers of observations. This research uses more than three thousand participant records spanning over three years from all Kentucky Drug Courts. Multiple logistic regression is used to determine which factors predict program completion. Participant characteristics, problem behaviors, and drug court variables are examined. Increase in age, earning at least a high school diploma, indicating methamphetamine or other stimulant as a drug of choice, and being married are associated with an increased likelihood of graduating. Carrying a charge related to the administration of justice and receiving a sanction involving incarceration are associated with a decrease in the likelihood of graduating. Drug court variables, which included the track through which one entered drug court and the length of time the drug court was in operation, are also associated with completion outcomes; however, the addition of these variables into a multivariate model reduced overall model performance. These findings should be used with caution, as the large sample size resulted in powerful statistics, finding even very small relationships statistically significant. To more firmly identify a predictive set of factors, future studies must balance power of the statistics with the utility of the findings and also explore the complex interactions among variables.
","abstract_html":"<p>This dissertation examines data collected from Kentucky Drug Court to determine factors associated with program completion outcomes. Extant research on drug court completion outcomes is generally limited to individual drug courts and includes small numbers of observations. This research uses more than three thousand participant records spanning over three years from all Kentucky Drug Courts. Multiple logistic regression is used to determine which factors predict program completion. Participant characteristics, problem behaviors, and drug court variables are examined. Increase in age, earning at least a high school diploma, indicating methamphetamine or other stimulant as a drug of choice, and being married are associated with an increased likelihood of graduating. Carrying a charge related to the administration of justice and receiving a sanction involving incarceration are associated with a decrease in the likelihood of graduating. Drug court variables, which included the track through which one entered drug court and the length of time the drug court was in operation, are also associated with completion outcomes; however, the addition of these variables into a multivariate model reduced overall model performance. These findings should be used with caution, as the large sample size resulted in powerful statistics, finding even very small relationships statistically significant. To more firmly identify a predictive set of factors, future studies must balance power of the statistics with the utility of the findings and also explore the complex interactions among variables.</p>","abstract_has_math":false,"creators":["Hagensen, Elizabeth R."],"institution":null,"degree_name":"Doctor of Philosophy (PhD)","degree_level":"Dissertation","degree_discipline":"Criminal Justice","degree_department":null,"school":null,"contributors":["Roni Mayzer"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2012,"date_issued":"2012-01-01T08:00:00Z","date_published":"2012-01-01T08:00:00Z","updated_at":"2026-07-24T03:26:17Z","subjects":["drug court, graduation, Kentucky, logistic regression, outcomes"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://commons.und.edu/theses/1290","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Roni Mayzer"]},{"key":"dc:creator","label":"Author","values":["Hagensen, Elizabeth R."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"thesis:degree_discipline","label":"Discipline","values":["Criminal Justice"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["drug court, graduation, Kentucky, logistic regression, outcomes"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://commons.und.edu/theses/1290"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This dissertation examines data collected from Kentucky Drug Court to determine factors associated with program completion outcomes. Extant research on drug court completion outcomes is generally limited to individual drug courts and includes small numbers of observations. This research uses more than three thousand participant records spanning over three years from all Kentucky Drug Courts. Multiple logistic regression is used to determine which factors predict program completion. Participant characteristics, problem behaviors, and drug court variables are examined. Increase in age, earning at least a high school diploma, indicating methamphetamine or other stimulant as a drug of choice, and being married are associated with an increased likelihood of graduating. Carrying a charge related to the administration of justice and receiving a sanction involving incarceration are associated with a decrease in the likelihood of graduating. Drug court variables, which included the track through which one entered drug court and the length of time the drug court was in operation, are also associated with completion outcomes; however, the addition of these variables into a multivariate model reduced overall model performance. These findings should be used with caution, as the large sample size resulted in powerful statistics, finding even very small relationships statistically significant. To more firmly identify a predictive set of factors, future studies must balance power of the statistics with the utility of the findings and also explore the complex interactions among variables.
"]},{"key":"dc:title","label":"Title","values":["Factors That Influence Program Completion: Predicting Kentucky Drug Court Completion Outcomes"]}]}],"canonical_facts":{"dc:contributor":["Roni Mayzer"],"dc:creator":["Hagensen, Elizabeth R."],"dc:description.abstract":["This dissertation examines data collected from Kentucky Drug Court to determine factors associated with program completion outcomes. Extant research on drug court completion outcomes is generally limited to individual drug courts and includes small numbers of observations. This research uses more than three thousand participant records spanning over three years from all Kentucky Drug Courts. Multiple logistic regression is used to determine which factors predict program completion. Participant characteristics, problem behaviors, and drug court variables are examined. Increase in age, earning at least a high school diploma, indicating methamphetamine or other stimulant as a drug of choice, and being married are associated with an increased likelihood of graduating. Carrying a charge related to the administration of justice and receiving a sanction involving incarceration are associated with a decrease in the likelihood of graduating. Drug court variables, which included the track through which one entered drug court and the length of time the drug court was in operation, are also associated with completion outcomes; however, the addition of these variables into a multivariate model reduced overall model performance. These findings should be used with caution, as the large sample size resulted in powerful statistics, finding even very small relationships statistically significant. To more firmly identify a predictive set of factors, future studies must balance power of the statistics with the utility of the findings and also explore the complex interactions among variables.
"],"dc:identifier":["https://commons.und.edu/theses/1290"],"dc:subject":["drug court, graduation, Kentucky, logistic regression, outcomes"],"dc:title":["Factors That Influence Program Completion: Predicting Kentucky Drug Court Completion Outcomes"],"thesis:degree_discipline":["Criminal Justice"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-07-24T03:26:17Z"}