Page 1 |
Save page Remove page | Previous | 1 of 318 | Next |
|
small (250x250 max)
medium (500x500 max)
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
Subset |
PRECISION-BASED SAMPLE SIZE REDUCTION FOR BAYESIAN
EXPERIMENTATION USING MARKOV CHAIN SIMULATION
by
David J. Huber
A Dissertation Presented to the
FACULTY OF THE GRADUATE SCHOOL
UNIVERSITY OF SOUTHERN CALIFORNIA
In Partial Fulfillment of the
Requirements for the Degree
DOCTOR OF PHILOSOPHY
(BIOMEDICAL ENGINEERING)
December 2007
Copyright 2007 David J. Huber
Object Description
| Title | Precision-based sample size reduction for Bayesian experimentation using Markov chain simulation |
| Author | Huber, David J. |
| Author email | huber@usc.edu |
| Degree | Doctor of Philosophy |
| Document type | Dissertation |
| Degree program | Biomedical Engineering |
| School | Viterbi School of Engineering |
| Date defended/completed | 2007-06-19 |
| Date submitted | 2007 |
| Restricted until | Unrestricted |
| Date published | 2007-10-25 |
| Advisor (committee chair) | Yamashiro, Stanley |
| Advisor (committee member) |
Schumitzky, Alan Maarek, Jean-Michel |
| Abstract | The costs of sampling are often quite high in biomedical engineering and medicine, where collecting data is frequently invasive, destructive, or time consuming. This results in experiments that are either sparse or very expensive. Optimal design strategies can help a researcher to make the most of a given number of experimental observations, but neglect the actual problem of sample size determination. For a grey-box experiment with continuous parameter and observation spaces, one must determine how many observations are required in order to ensure precise parameter estimates that resist experimental error and prior uncertainty in the parameter values. This work proposes a novel approach to sample size determination that bridges experimental science with principles of quality engineering and control. A population of parallel Markov chains is simulated from the preposterior distribution to generate posterior predictive distributions for a proposed experiment. This represents a collection of possible posterior distributions for the experiment over the entire observation space. One can compute the estimator precision and determine the optimal sample size as a measure of the probability that the experiment, on the average, will fail to yield a necessary degree of estimator precision. This work evaluates the proposed method by applying it to a combination of simulated and practical experiments that validate the utility of the algorithm and examine its properties under various prior distributions and degrees of experimental error. A specialized software package was created to carry out the computations necessary for precision-based sample size determination. |
| Keyword | sample size determination; bayes; experiment design; system modeling |
| Language | English |
| Part of collection | University of Southern California dissertations and theses |
| Publisher (of the original version) | University of Southern California |
| Place of publication (of the original version) | Los Angeles, California |
| Publisher (of the digital version) | University of Southern California. Libraries |
| Type | texts |
| Legacy record ID | usctheses-m887 |
| Rights | Huber, David J. |
| Repository name | Libraries, University of Southern California |
| Repository address | Los Angeles, California |
| Repository email | http://www.usc.edu/isd/libraries/services/ask_a_librarian/email/ |
| Filename | etd-Huber-20071025 |
| Archival file | uscthesesreloadpub_Volume44/etd-Huber-20071025.pdf |
Description
| Title | Page 1 |
| Full text | PRECISION-BASED SAMPLE SIZE REDUCTION FOR BAYESIAN EXPERIMENTATION USING MARKOV CHAIN SIMULATION by David J. Huber A Dissertation Presented to the FACULTY OF THE GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Fulfillment of the Requirements for the Degree DOCTOR OF PHILOSOPHY (BIOMEDICAL ENGINEERING) December 2007 Copyright 2007 David J. Huber |
Comments
Post a Comment for Page 1
