國立虎尾科技大學 |

Essays in Macroeconomics, Health Care, and Machine Learning.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Essays in Macroeconomics, Health Care, and Machine Learning./
作者:	Leslie, Jonathan.
面頁冊數:	1 online resource (157 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
標題:	Public policy. -
電子資源:	click for full text (PQDT)
ISBN:	9798382605814

Essays in Macroeconomics, Health Care, and Machine Learning.
Leslie, Jonathan.

Essays in Macroeconomics, Health Care, and Machine Learning. - 1 online resource (157 pages)

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

Thesis (Ph.D.)--Indiana University, 2024.

Includes bibliographical references

In my dissertation, I develop structural life-cycle models populated by overlapping generations of heterogeneous households to quantitatively evaluate economic and welfare implications related to health outcomes and uncertainties while additionally exploring the integration of deep machine learning techniques in economic prediction and forecasting applications. In the first chapter, I quantitatively evaluate the impact of individuals' lifetime health and health care use dynamics on macroeconomic outcomes, including how the measurement of these dynamics affects estimates under changing socio-demographic and policy settings. I embed a dynamic model governing the stochastic lifetime evolution of both health and empirically-identified necessary health care use within a life-cycle model containing overlapping generations of heterogeneous households and consider three settings: a base U.S. economy scenario, a population age shift to 2070 demographic projections, and a policy reform that increases Medicare generosity. Through shaping underlying population health and the financial risk of health care utilization, health and health care dynamics over the life cycle are an important driver of consumption inequality, public finance, and macroeconomic aggregates in the calibrated model. Effects on outcomes such as income inequality are further highlighted when comparing the baseline model to coarser means of measuring health and health care use that are commonly used in related literature.The second chapter examines the economic and welfare impacts of publicly-subsidizing the production of a good or service that is characterized by uncertain utilization via the context of medical physicians and health care services in the United States. The financial risk to individuals of uncertain health care expenditure throughout life creates the potential for the subsidization of health care factors of production to increase welfare through decreasing the cost of health care and thus household exposure to risk. To evaluate this mechanism, I perform policy experiments in a life-cycle model with a health care sector, physicians, and heterogeneous households with uncertain health. In the model, publicly-funding the private financial costs of physician training in the U.S. through subsidies or cash transfers increases physicians per capita, decreases health care costs and aggregate expenditure, and increases lifetime welfare by up to 0.55 percent of annual consumption per year on average when transfers are equal to the full value of medical school tuition.The third chapter presents a method for forecasting with high-dimensional, spatially-distributed economic data via borrowing techniques from visual recognition machine learning. Specifically, I cast the time series of spatially-disaggregated U.S. economic data as a temporal sequence of geographic 'images' in a computer vision setting and develop a deep learning model architecture to evaluate whether leveraging the spatio-temporal distribution of data features can improve macroeconomic forecasts. The resulting recurrent convolutional neural network model accurately forecasts changes in U.S. GDP and outperforms more traditional linear methods as well as deep learning models that do not utilize the data's spatial distribution. Analysis of the estimated model provides intuition for its improved performance by highlighting an ability to focus on regional economic experiences.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798382605814Subjects--Topical Terms:

1002398
Public policy.
Subjects--Index Terms:

Macroeconomic outcomesIndex Terms--Genre/Form:

554714
Electronic books.

Essays in Macroeconomics, Health Care, and Machine Learning.
LDR:04780ntm a22003857 4500 001 1147581
005 20240909103817.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382605814
035 $a (MiAaPQ)AAI31241489
035 $a AAI31241489
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Leslie, Jonathan. $3 1473338
245 1 0 $a Essays in Macroeconomics, Health Care, and Machine Learning.
264 0 $c 2024
300 $a 1 online resource (157 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
500 $a Advisor: Guler, Bulent.
502 $a Thesis (Ph.D.)--Indiana University, 2024.
504 $a Includes bibliographical references
520 $a In my dissertation, I develop structural life-cycle models populated by overlapping generations of heterogeneous households to quantitatively evaluate economic and welfare implications related to health outcomes and uncertainties while additionally exploring the integration of deep machine learning techniques in economic prediction and forecasting applications. In the first chapter, I quantitatively evaluate the impact of individuals' lifetime health and health care use dynamics on macroeconomic outcomes, including how the measurement of these dynamics affects estimates under changing socio-demographic and policy settings. I embed a dynamic model governing the stochastic lifetime evolution of both health and empirically-identified necessary health care use within a life-cycle model containing overlapping generations of heterogeneous households and consider three settings: a base U.S. economy scenario, a population age shift to 2070 demographic projections, and a policy reform that increases Medicare generosity. Through shaping underlying population health and the financial risk of health care utilization, health and health care dynamics over the life cycle are an important driver of consumption inequality, public finance, and macroeconomic aggregates in the calibrated model. Effects on outcomes such as income inequality are further highlighted when comparing the baseline model to coarser means of measuring health and health care use that are commonly used in related literature.The second chapter examines the economic and welfare impacts of publicly-subsidizing the production of a good or service that is characterized by uncertain utilization via the context of medical physicians and health care services in the United States. The financial risk to individuals of uncertain health care expenditure throughout life creates the potential for the subsidization of health care factors of production to increase welfare through decreasing the cost of health care and thus household exposure to risk. To evaluate this mechanism, I perform policy experiments in a life-cycle model with a health care sector, physicians, and heterogeneous households with uncertain health. In the model, publicly-funding the private financial costs of physician training in the U.S. through subsidies or cash transfers increases physicians per capita, decreases health care costs and aggregate expenditure, and increases lifetime welfare by up to 0.55 percent of annual consumption per year on average when transfers are equal to the full value of medical school tuition.The third chapter presents a method for forecasting with high-dimensional, spatially-distributed economic data via borrowing techniques from visual recognition machine learning. Specifically, I cast the time series of spatially-disaggregated U.S. economic data as a temporal sequence of geographic 'images' in a computer vision setting and develop a deep learning model architecture to evaluate whether leveraging the spatio-temporal distribution of data features can improve macroeconomic forecasts. The resulting recurrent convolutional neural network model accurately forecasts changes in U.S. GDP and outperforms more traditional linear methods as well as deep learning models that do not utilize the data's spatial distribution. Analysis of the estimated model provides intuition for its improved performance by highlighting an ability to focus on regional economic experiences.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Public policy. $3 1002398
653 $a Macroeconomic outcomes
653 $a Public finance
653 $a Neural network
653 $a Machine learning
655 7 $a Electronic books. $2 local $3 554714
690 $a 0501
690 $a 0630
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Indiana University. $b Economics. $3 1179085
773 0 $t Dissertations Abstracts International $g 85-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31241489 $z click for full text (PQDT)