Exploring Bayesian credible intervals for common epidemiologic effect measures based on cross-sectional data Público

Abstract

As the limitations of standard Wald-type methods to estimate the confidence intervals for

the difference of proportions, relative risk, and odds ratio in 2 × 2 contingency tables are

well recognized, we investigated the frequentist performance of alternative Bayesian

credible intervals. We used simulation studies to compare the coverage rates and widths of

these competing sorts of confidence intervals. As a new proposal, we also put forth an

adjusted credible interval which used two different Dirichlet priors to get the lower and

upper limits of the confidence intervals. In small sample settings, this method appears to

greatly reduce average interval width compared to Wald-type approaches, while

maintaining far better coverage rates compared to more standard credible intervals based

on a single Dirichlet prior.

Table of Contents

Table of Contents

1. Introduction .................................................................................................................................. 1

2.Methods ........................................................................................................................................ 3

2.1 Standard Wald intervals ......................................................................................................... 4

2.2 Gart intervals and adjusted Gart intervals .............................................................................. 5

2.3 Bayesian credible intervals .................................................................................................... 6

2.4 Simulation process ................................................................................................................. 8

3. Results ........................................................................................................................................ 10

4. Discussion .................................................................................................................................. 19

Bibliography .................................................................................................................................. 22

About this Master's Thesis

Rights statement

• Permission granted by the author to include this thesis or dissertation in this repository. All rights reserved by the author. Please contact the author for information regarding the reproduction and use of this thesis or dissertation.

School	Rollins School of Public Health
Department	Biostatistics
Subfield / Discipline	Biostatistics - MPH & MSPH
Degree	M.S.P.H.
Submission	Master's Thesis
Language	English
Research Field	Biology, Biostatistics Health Sciences, Epidemiology
Palavra-chave	Bayesian method Confidence interval Odds ratio Relative risk Risk difference
Committee Chair / Thesis Advisor	Robert Lyles, Emory University
Committee Members	Michael Haber, Emory University

Última modificação

Primary PDF

Thumbnail	Title	Date Uploaded	Actions
	Exploring Bayesian credible intervals for common epidemiologic effect measures based on cross-sectional data ()	2020-04-15 17:00:34 -0400	Press to Select an action Download

Supplemental Files

Thumbnail	Title	Date Uploaded	Actions