{"id":{"repo_id":"utc","oai_identifier":"oai:scholar.utc.edu:theses-1950"},"canonical_url":"https://search.dev.ndltd.org/etd/utc/oai:scholar.utc.edu:theses-1950","repository":{"repo_id":"utc","name":"University of Tennessee - Chattanooga","base_url":"https://scholar.utc.edu/do/oai/"},"display":{"title":"Predicting enrollment in a metropolitan university in southeast Tennessee","abstract":"Institutions of higher education are tasked with making decisions that will impact their students, faculty, staff, and other stakeholders. Many of these decisions are focused on varying aspects of budgeting, and an institution’s sustainability and reputation could be impacted by misallocations of resources. Some of this risk could potentially be eliminated if there was a strategic way to predict which data points have meaningful impact on student enrollment. This study used data collected at a metropolitan university in Southeast Tennessee for six fall semesters to develop enrollment prediction models for the institution. The focus of the study was to determine whether one or more variables could be used to predict undergraduate student headcount at a 4-year university based on one or more student demographic and attribute variables. Using Markov Chain Monte Carlo (MCMC) simulation allowed for a more instinctive way to derive statistical methods by enabling probability estimation for hypotheses. The first step, linear regression, demonstrated there were specific sets of predictor variables for institutional enrollment and for four academic programs’ enrollment; no two models included the same variables. Subsequently, it was determined that the MCMC simulation models were able to accurately predict institutional and program enrollment for specific fall semesters, but not for all fall semesters, perhaps due to limitations related to COVID-19. While the enrollment prediction models developed were not accurate for each fall semester, it is important to note that having some type of estimation and a place to start with potential enrollment provide a huge benefit to individual academic programs as well as to the institution. Previously, there has not been a consistent or comparable way to make estimates of enrollment; however, using data that are readily available and considering variables that are not typically utilized provides a way to develop robust models for use at the institution. This model can be adapted for individual programs, and it is likely that each academic program would include different predictor variables. Those in leadership positions can benefit from better estimating the number of students to be enrolled in order to allocate resources appropriately, which helps facilitate student success.","abstract_html":"Institutions of higher education are tasked with making decisions that will impact their students, faculty, staff, and other stakeholders. Many of these decisions are focused on varying aspects of budgeting, and an institution’s sustainability and reputation could be impacted by misallocations of resources. Some of this risk could potentially be eliminated if there was a strategic way to predict which data points have meaningful impact on student enrollment. This study used data collected at a metropolitan university in Southeast Tennessee for six fall semesters to develop enrollment prediction models for the institution. The focus of the study was to determine whether one or more variables could be used to predict undergraduate student headcount at a 4-year university based on one or more student demographic and attribute variables. Using Markov Chain Monte Carlo (MCMC) simulation allowed for a more instinctive way to derive statistical methods by enabling probability estimation for hypotheses. The first step, linear regression, demonstrated there were specific sets of predictor variables for institutional enrollment and for four academic programs’ enrollment; no two models included the same variables. Subsequently, it was determined that the MCMC simulation models were able to accurately predict institutional and program enrollment for specific fall semesters, but not for all fall semesters, perhaps due to limitations related to COVID-19. While the enrollment prediction models developed were not accurate for each fall semester, it is important to note that having some type of estimation and a place to start with potential enrollment provide a huge benefit to individual academic programs as well as to the institution. Previously, there has not been a consistent or comparable way to make estimates of enrollment; however, using data that are readily available and considering variables that are not typically utilized provides a way to develop robust models for use at the institution. This model can be adapted for individual programs, and it is likely that each academic program would include different predictor variables. Those in leadership positions can benefit from better estimating the number of students to be enrolled in order to allocate resources appropriately, which helps facilitate student success.","abstract_has_math":false,"creators":["Williamson, Cynthia"],"institution":"University of Tennessee at Chattanooga","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Rausch, David W.","Crawford, Elizabeth K.; Harbison, John W.; Freeman Sr., Yancy E.","College of Health, Education, and Professional Studies"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-12-31T08:00:00Z","date_published":"2023-12-31T08:00:00Z","updated_at":"2026-07-24T05:47:06Z","subjects":["Education, Higher--United States--Forecasting","Education--Demographic aspects--United States","Universities and colleges--United States--Administration"],"languages":["English","eng"],"rights":[],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["xii, 94 leaves"],"render_values":[{"text":"xii, 94 leaves","href":null,"code":true}]}]},"links":{"outbound_url":"https://scholar.utc.edu/theses/775","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Rausch, David W.","Crawford, Elizabeth K.; Harbison, John W.; Freeman Sr., Yancy E.","College of Health, Education, and Professional Studies"]},{"key":"dc:creator","label":"Author","values":["Williamson, Cynthia"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-12-01T08:00:00Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-12-31T08:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["University of Tennessee at Chattanooga","Chattanooga (Tenn.)"]},{"key":"dc:relation","label":"Dc Relation","values":["Masters Theses and Doctoral Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["Doctoral dissertations","Text"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Education, Higher--United States--Forecasting","Education--Demographic aspects--United States","Universities and colleges--United States--Administration"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["xii, 94 leaves","https://scholar.utc.edu/theses/775"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["School of Professional Studies","Ph. D.; A dissertation submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Doctor of Philosophy."]},{"key":"dc:description.abstract","label":"Abstract","values":["Institutions of higher education are tasked with making decisions that will impact their students, faculty, staff, and other stakeholders. Many of these decisions are focused on varying aspects of budgeting, and an institution’s sustainability and reputation could be impacted by misallocations of resources. Some of this risk could potentially be eliminated if there was a strategic way to predict which data points have meaningful impact on student enrollment. This study used data collected at a metropolitan university in Southeast Tennessee for six fall semesters to develop enrollment prediction models for the institution. The focus of the study was to determine whether one or more variables could be used to predict undergraduate student headcount at a 4-year university based on one or more student demographic and attribute variables. Using Markov Chain Monte Carlo (MCMC) simulation allowed for a more instinctive way to derive statistical methods by enabling probability estimation for hypotheses. The first step, linear regression, demonstrated there were specific sets of predictor variables for institutional enrollment and for four academic programs’ enrollment; no two models included the same variables. Subsequently, it was determined that the MCMC simulation models were able to accurately predict institutional and program enrollment for specific fall semesters, but not for all fall semesters, perhaps due to limitations related to COVID-19. While the enrollment prediction models developed were not accurate for each fall semester, it is important to note that having some type of estimation and a place to start with potential enrollment provide a huge benefit to individual academic programs as well as to the institution. Previously, there has not been a consistent or comparable way to make estimates of enrollment; however, using data that are readily available and considering variables that are not typically utilized provides a way to develop robust models for use at the institution. This model can be adapted for individual programs, and it is likely that each academic program would include different predictor variables. Those in leadership positions can benefit from better estimating the number of students to be enrolled in order to allocate resources appropriately, which helps facilitate student success."]},{"key":"dc:title","label":"Title","values":["Predicting enrollment in a metropolitan university in southeast Tennessee"]}]}],"canonical_facts":{"dc:contributor":["Rausch, David W.","Crawford, Elizabeth K.; Harbison, John W.; Freeman Sr., Yancy E.","College of Health, Education, and Professional Studies"],"dc:creator":["Williamson, Cynthia"],"dc:date":["2022-12-01T08:00:00Z"],"dc:date.available":["2023-12-31T08:00:00Z"],"dc:description":["School of Professional Studies","Ph. D.; A dissertation submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Doctor of Philosophy."],"dc:description.abstract":["Institutions of higher education are tasked with making decisions that will impact their students, faculty, staff, and other stakeholders. Many of these decisions are focused on varying aspects of budgeting, and an institution’s sustainability and reputation could be impacted by misallocations of resources. Some of this risk could potentially be eliminated if there was a strategic way to predict which data points have meaningful impact on student enrollment. This study used data collected at a metropolitan university in Southeast Tennessee for six fall semesters to develop enrollment prediction models for the institution. The focus of the study was to determine whether one or more variables could be used to predict undergraduate student headcount at a 4-year university based on one or more student demographic and attribute variables. Using Markov Chain Monte Carlo (MCMC) simulation allowed for a more instinctive way to derive statistical methods by enabling probability estimation for hypotheses. The first step, linear regression, demonstrated there were specific sets of predictor variables for institutional enrollment and for four academic programs’ enrollment; no two models included the same variables. Subsequently, it was determined that the MCMC simulation models were able to accurately predict institutional and program enrollment for specific fall semesters, but not for all fall semesters, perhaps due to limitations related to COVID-19. While the enrollment prediction models developed were not accurate for each fall semester, it is important to note that having some type of estimation and a place to start with potential enrollment provide a huge benefit to individual academic programs as well as to the institution. Previously, there has not been a consistent or comparable way to make estimates of enrollment; however, using data that are readily available and considering variables that are not typically utilized provides a way to develop robust models for use at the institution. This model can be adapted for individual programs, and it is likely that each academic program would include different predictor variables. Those in leadership positions can benefit from better estimating the number of students to be enrolled in order to allocate resources appropriately, which helps facilitate student success."],"dc:identifier":["xii, 94 leaves","https://scholar.utc.edu/theses/775"],"dc:language":["English","eng"],"dc:publisher":["University of Tennessee at Chattanooga","Chattanooga (Tenn.)"],"dc:relation":["Masters Theses and Doctoral Dissertations"],"dc:rights":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Education, Higher--United States--Forecasting","Education--Demographic aspects--United States","Universities and colleges--United States--Administration"],"dc:title":["Predicting enrollment in a metropolitan university in southeast Tennessee"],"dc:type":["Doctoral dissertations","Text"]},"updated_at":"2026-07-24T05:47:06Z"}