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

A dynamic model of patient learning ...

Fernandez, Jose M.

FindBook

Google Book

Amazon

博客來

A dynamic model of patient learning and attrition using clinical trial data.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	A dynamic model of patient learning and attrition using clinical trial data./
作者:	Fernandez, Jose M.
面頁冊數:	144 p.
附註:	Adviser: John V. Pepper.
Contained By:	Dissertation Abstracts International69-02A.
標題:	Economics, General. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3302216
ISBN:	9780549476146

A dynamic model of patient learning and attrition using clinical trial data.
Fernandez, Jose M.

A dynamic model of patient learning and attrition using clinical trial data. - 144 p.

Adviser: John V. Pepper.

Thesis (Ph.D.)--University of Virginia, 2008.

In this dissertation, I present an empirical model of learning under ambiguity in the context of clinical trials. Patients are concerned with learning the treatment effect of the experimental drug, but face the ambiguity of random group assignment. A two dimensional Bayesian model of learning is proposed to capture patients' beliefs on the treatment effect and group assignment These beliefs are then used to predict patient attrition in clinical trials. Patient learning is demonstrated to be slower when taking into account group ambiguity. In addition, the model corrects for attrition bias in the estimated treatment affect.

ISBN: 9780549476146Subjects--Topical Terms:

1017424
Economics, General.

A dynamic model of patient learning and attrition using clinical trial data.
LDR:03157nam 2200301 a 45 001 947302
005 20110524
008 110524s2008 ||||||||||||||||| ||eng d
020 $a 9780549476146
035 $a (UMI)AAI3302216
035 $a AAI3302216
040 $a UMI $c UMI
100 1 $a Fernandez, Jose M. $3 1270767
245 1 2 $a A dynamic model of patient learning and attrition using clinical trial data.
300 $a 144 p.
500 $a Adviser: John V. Pepper.
500 $a Source: Dissertation Abstracts International, Volume: 69-02, Section: A, page: 0684.
502 $a Thesis (Ph.D.)--University of Virginia, 2008.
520 $a In this dissertation, I present an empirical model of learning under ambiguity in the context of clinical trials. Patients are concerned with learning the treatment effect of the experimental drug, but face the ambiguity of random group assignment. A two dimensional Bayesian model of learning is proposed to capture patients' beliefs on the treatment effect and group assignment These beliefs are then used to predict patient attrition in clinical trials. Patient learning is demonstrated to be slower when taking into account group ambiguity. In addition, the model corrects for attrition bias in the estimated treatment affect.
520 $a Two contributions are made in this work. First, the structural model proposed in this dissertation is the first to estimate a model of learning under group assignment ambiguity. The model allows patients to update beliefs on treatment effects and treatment group assignment, simultaneously. Data from two clinical trials are used to estimate the structural model. The first trial studies the effect of AZT as a treatment in HIV patients. Structural model estimates of health indicating that placebo group health returns are nearly half the size of those found using traditional methods. The primary factors causing attrition are blood related side effects. Learning under group assignment ambiguity leads patients in the placebo group to incorrectly infer that they are in the treatment group. The second experiment examines the effect of Topamax to treat alcohol addiction. Structural model estimates of health in this study are nearly three times larger than those found using traditional methods. In addition, the side effect parathesia conveys information about group assignment, thereby having a negative effect on attrition.
520 $a The second contribution is the study of patient experimentation. Previous models have examined agent experimentation in the form of patients switching between drugs. This dissertation models patient experimentation as a continuous choice, where patients vary dose consumption of the drug to increase learning rates. This model is estimated using data from the Topamax study. The model captures patient non-compliant behavior as a mix of experimental learning and side effect avoidance.
590 $a School code: 0246.
650 4 $a Economics, General. $3 1017424
650 4 $a Health Sciences, General. $3 1017817
690 $a 0501
690 $a 0566
710 2 $a University of Virginia. $3 645578
773 0 $t Dissertation Abstracts International $g 69-02A.
790 $a 0246
790 1 0 $a Pepper, John V., $e advisor
791 $a Ph.D.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3302216