東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Essays on the demand for health, hea...

Wang, Rui.

FindBook

Google Book

Amazon

博客來

Essays on the demand for health, health insurance, and medical care.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Essays on the demand for health, health insurance, and medical care./
作者:	Wang, Rui.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2008,
面頁冊數:	115 p.
附註:	Source: Dissertations Abstracts International, Volume: 70-11, Section: A.
Contained By:	Dissertations Abstracts International70-11A.
標題:	Studies. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3347680
ISBN:	9781109033571

Essays on the demand for health, health insurance, and medical care.
Wang, Rui.

Essays on the demand for health, health insurance, and medical care. - Ann Arbor : ProQuest Dissertations & Theses, 2008 - 115 p.

Source: Dissertations Abstracts International, Volume: 70-11, Section: A.

Thesis (Ph.D.)--University of Hawai'i at Manoa, 2008.

This item must not be sold to any third party vendors.

This dissertation consists of three essays that address two distinct topics in health economics: (1) optimal health investment and optimal insurance under ex ante moral hazard within a dynamic stochastic human capital framework; and (2) statistical modeling of medical care utilization data based on individual characteristics. The first essay presents a dynamic stochastic model of health investment with health insurance. A representative individual's lifecycle behavior of consumption and investment in health capital is then examined within a continuous-time optimal control framework. With the introduction of health insurance, individual health investment behavior exhibits ex ante moral hazard, and the conditions for optimal health investment under health insurance are derived. A statistical model becomes overfitted when the number of free parameters employed becomes excessive. Models of medical care utilization risk overfitting due to the large number of free parameters involved. The second essay addresses the overfitting problem in the modeling of health care utilization count data by proposing a zero augmented negative binomial model (ZANB). In contrast to the popular two-part model approaches, where the binary and the count processes are modeled with two separate data-generating processes, ZANB conforms the two processes by imposing that parameters from the binary model and parameters from the count model should be linear transformations of each other. This constraint effectively reduces the number of free parameters by nearly one half to mitigate the risk of overfitting. In addition to the theoretical appeals, analyses using survey data confirm the good statistical properties and demonstrate superior prediction accuracy of this new estimation scheme. The third essay proposes a pseudo-full information estimation scheme (PFIE) that promotes model simplicity (and hence parameter stability) at the cost of model specification. PFIE is useful in the modeling of multiple data generating processes (DGP) where parameters from distinct DGP's are correlated. By imposing constraints on parameters based on their correlation, the number of free parameters in the model can be greatly reduced. Essay Three conducts a number of Monte Carlo simulation experiments to numerically examine the statistical properties of PFIE under various parametric assumptions.

ISBN: 9781109033571Subjects--Topical Terms:

3433795
Studies.
Subjects--Index Terms:

Health

Essays on the demand for health, health insurance, and medical care.
LDR:03641nmm a2200385 4500 001 2395940
005 20240531084212.5
006 m o d
007 cr#unu||||||||
008 251215s2008 ||||||||||||||||| ||eng d
020 $a 9781109033571
035 $a (MiAaPQ)AAI3347680
035 $a AAI3347680
040 $a MiAaPQ $c MiAaPQ
100 1 $a Wang, Rui. $3 866052
245 1 0 $a Essays on the demand for health, health insurance, and medical care.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2008
300 $a 115 p.
500 $a Source: Dissertations Abstracts International, Volume: 70-11, Section: A.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Russo, Gerard.
502 $a Thesis (Ph.D.)--University of Hawai'i at Manoa, 2008.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
520 $a This dissertation consists of three essays that address two distinct topics in health economics: (1) optimal health investment and optimal insurance under ex ante moral hazard within a dynamic stochastic human capital framework; and (2) statistical modeling of medical care utilization data based on individual characteristics. The first essay presents a dynamic stochastic model of health investment with health insurance. A representative individual's lifecycle behavior of consumption and investment in health capital is then examined within a continuous-time optimal control framework. With the introduction of health insurance, individual health investment behavior exhibits ex ante moral hazard, and the conditions for optimal health investment under health insurance are derived. A statistical model becomes overfitted when the number of free parameters employed becomes excessive. Models of medical care utilization risk overfitting due to the large number of free parameters involved. The second essay addresses the overfitting problem in the modeling of health care utilization count data by proposing a zero augmented negative binomial model (ZANB). In contrast to the popular two-part model approaches, where the binary and the count processes are modeled with two separate data-generating processes, ZANB conforms the two processes by imposing that parameters from the binary model and parameters from the count model should be linear transformations of each other. This constraint effectively reduces the number of free parameters by nearly one half to mitigate the risk of overfitting. In addition to the theoretical appeals, analyses using survey data confirm the good statistical properties and demonstrate superior prediction accuracy of this new estimation scheme. The third essay proposes a pseudo-full information estimation scheme (PFIE) that promotes model simplicity (and hence parameter stability) at the cost of model specification. PFIE is useful in the modeling of multiple data generating processes (DGP) where parameters from distinct DGP's are correlated. By imposing constraints on parameters based on their correlation, the number of free parameters in the model can be greatly reduced. Essay Three conducts a number of Monte Carlo simulation experiments to numerically examine the statistical properties of PFIE under various parametric assumptions.
590 $a School code: 0085.
650 4 $a Studies. $3 3433795
650 4 $a Population. $3 518693
650 4 $a Investments. $3 566987
650 4 $a Random variables. $3 646291
650 4 $a Optimization. $3 891104
650 4 $a Personal health. $3 3544029
650 4 $a Expenditures. $3 3556049
650 4 $a Simulation. $3 644748
650 4 $a Experiments. $3 525909
650 4 $a Health care. $3 2213177
650 4 $a Medical research. $2 bicssc $3 1556686
650 4 $a Preferences. $3 3560350
650 4 $a Essays. $3 642973
653 $a Health
653 $a Health insurance
653 $a Medical care
690 $a 0501
690 $a 0511
710 2 $a University of Hawai'i at Manoa. $3 1017511
773 0 $t Dissertations Abstracts International $g 70-11A.
790 $a 0085
791 $a Ph.D.
792 $a 2008
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3347680