A hierarchical non-homogenous Poisson model for meta-analysis of adenoma counts

Carolyn M. Rutter, Onchee Yu, Diana L Miglioretti

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

We use a hierarchical model for a meta-analysis that combines information from autopsy studies of adenoma prevalence and counts. The studies we included reported findings using a variety of adenoma prevalence groupings and age categories. We use a non-homogeneous Poisson model for multinomial bin probabilities. The Poisson model allows risk to depend on age and sex, and incorporates extra-Poisson variability. We evaluate model fit using the posterior predicted distribution of adenoma prevalence reported by the studies included in our analyses and validate our model using adenoma prevalence reported by more recent colonoscopy studies. For 1990, the estimated adenoma prevalence among Americans at age 60 is 40.3 per cent for men compared to 29.2 per cent for women.

Original languageEnglish (US)
Pages (from-to)98-109
Number of pages12
JournalStatistics in Medicine
Volume26
Issue number1
DOIs
StatePublished - Jan 15 2007
Externally publishedYes

Fingerprint

Poisson Model
Adenoma
Meta-Analysis
Count
Cross-Sectional Studies
Hierarchical Model
Colonoscopy
Posterior distribution
Grouping
Autopsy
Siméon Denis Poisson
Evaluate
Model

Keywords

  • Bayesian estimation
  • Goodness of fit
  • Model validation

ASJC Scopus subject areas

  • Epidemiology

Cite this

A hierarchical non-homogenous Poisson model for meta-analysis of adenoma counts. / Rutter, Carolyn M.; Yu, Onchee; Miglioretti, Diana L.

In: Statistics in Medicine, Vol. 26, No. 1, 15.01.2007, p. 98-109.

Research output: Contribution to journalArticle

@article{4b3353198c13496682999ea4ee1f0fdb,
title = "A hierarchical non-homogenous Poisson model for meta-analysis of adenoma counts",
abstract = "We use a hierarchical model for a meta-analysis that combines information from autopsy studies of adenoma prevalence and counts. The studies we included reported findings using a variety of adenoma prevalence groupings and age categories. We use a non-homogeneous Poisson model for multinomial bin probabilities. The Poisson model allows risk to depend on age and sex, and incorporates extra-Poisson variability. We evaluate model fit using the posterior predicted distribution of adenoma prevalence reported by the studies included in our analyses and validate our model using adenoma prevalence reported by more recent colonoscopy studies. For 1990, the estimated adenoma prevalence among Americans at age 60 is 40.3 per cent for men compared to 29.2 per cent for women.",
keywords = "Bayesian estimation, Goodness of fit, Model validation",
author = "Rutter, {Carolyn M.} and Onchee Yu and Miglioretti, {Diana L}",
year = "2007",
month = "1",
day = "15",
doi = "10.1002/sim.2460",
language = "English (US)",
volume = "26",
pages = "98--109",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

TY - JOUR

T1 - A hierarchical non-homogenous Poisson model for meta-analysis of adenoma counts

AU - Rutter, Carolyn M.

AU - Yu, Onchee

AU - Miglioretti, Diana L

PY - 2007/1/15

Y1 - 2007/1/15

N2 - We use a hierarchical model for a meta-analysis that combines information from autopsy studies of adenoma prevalence and counts. The studies we included reported findings using a variety of adenoma prevalence groupings and age categories. We use a non-homogeneous Poisson model for multinomial bin probabilities. The Poisson model allows risk to depend on age and sex, and incorporates extra-Poisson variability. We evaluate model fit using the posterior predicted distribution of adenoma prevalence reported by the studies included in our analyses and validate our model using adenoma prevalence reported by more recent colonoscopy studies. For 1990, the estimated adenoma prevalence among Americans at age 60 is 40.3 per cent for men compared to 29.2 per cent for women.

AB - We use a hierarchical model for a meta-analysis that combines information from autopsy studies of adenoma prevalence and counts. The studies we included reported findings using a variety of adenoma prevalence groupings and age categories. We use a non-homogeneous Poisson model for multinomial bin probabilities. The Poisson model allows risk to depend on age and sex, and incorporates extra-Poisson variability. We evaluate model fit using the posterior predicted distribution of adenoma prevalence reported by the studies included in our analyses and validate our model using adenoma prevalence reported by more recent colonoscopy studies. For 1990, the estimated adenoma prevalence among Americans at age 60 is 40.3 per cent for men compared to 29.2 per cent for women.

KW - Bayesian estimation

KW - Goodness of fit

KW - Model validation

UR - http://www.scopus.com/inward/record.url?scp=33846188051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846188051&partnerID=8YFLogxK

U2 - 10.1002/sim.2460

DO - 10.1002/sim.2460

M3 - Article

C2 - 16372387

AN - SCOPUS:33846188051

VL - 26

SP - 98

EP - 109

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 1

ER -