Title page for ETD etd-08192007-090524

Type of Document

Dissertation

Author

Marker, Mahtab T

URN

etd-08192007-090524

Title

A Bayesian Approach to meta-regression: the Relationship between Body Mass Index and All-cause Mortality

Degree

Doctor of Philosophy

Department

Statistics, Department of

Advisory Committee

Advisor Name	Title
Daniel McGee	Committee Chair
Fred Huffer	Committee Member
Xufeng Niu	Committee Member

Keywords

Bayesian Hierarchical Models
Frailty Models
BMI
Meta-Analysis
Meta-Regression

Date of Defense

2007-07-03

Availability

unrestricted

Abstract

This thesis presents a Bayesian approach to Meta-Regression and Individual Patient Data (IPD) Meta-analysis. The focus of the research is on establishing the relationship between Body Mass Index (BMI) and all-cause mortality. This has been an area of continuing interest in the medical and public health communities and no concensus has been reached on what the optimal weight for individuals is. Standards are usually speci ed in terms of body mass index (BMI = wt(kg) over height(m)2 ) which is associated with body fat percentage.
Many studies in the literature have modelled the relationship between BMI and mortality and reported a
variety of relationships including U-shaped, J-shaped and linear curves.
The aim of my research was to use statistical methods to determine whether we can combine these diverse
results an obtain single estimated relationship, using which one can nd the point of minimum mortality and
establish reasonable ranges for optimal BMI or how we can best examine the reasons for the heterogeneity of
results. Commonly used techniques of Meta-analysis and Meta-regression are explored and a problem with
the estimation procedure in the multivariate setting is presented. A Bayesian approach using Hierarchical
Generalized Linear Mixed Model is suggested and implemented to overcome this drawback of standard
estimation techniques.
Another area which is explored brie°y is that of Individual Patient Data meta-analysis. A Frailty model or
Random E®ects Proportional Hazards Survival model approach is proposed to carry out IPD meta-regression
and come up with a single estimated relationship between BMI and mortality, adjusting for the variation
between studies.

Files

Filename		Size	Approximate Download Time (Hours:Minutes:Seconds)
Filename		Size	28.8 Modem	56K Modem	ISDN (64 Kb)	ISDN (128 Kb)	Higher-speed Access
	MarkerMFall2007.pdf	49.42 Mb	03:48:48	01:57:40	01:42:57	00:51:28	00:04:23