[Statlist] Research Seminar in Statistics *FRIDAY 5 OCTOBER 2018* GSEM, University of Geneva

[gsem-support-instituts]

Dear All,

We are pleased to invite you to our next Research Seminar.

Looking forward to seeing you

Organizers :                                                                                   
E. Cantoni - S. Engelke - D. La Vecchia - E. Ronchetti
S. Sperlich - F. Trojani - M.-P. Victoria-Feser

FRIDAY 5 OCTOBER 2018 at 11:15am, Uni-Mail M 5220

A Bayesian hierarchical model to integrate dietary exposure and biomarker measurements for the risk of kidney and lung cancer
Marta PITTAVINO - University of Geneva, Geneva School of Economics and Management, Research Center for Statistics

ABSTRACT:

In nutritional epidemiology, self-reported assessments of dietary exposure are prone to measurement errors. Estimates of the association between dietary factors and risk of disease can be biased. It was suggested to complement self-reported dietary assessments with objective measurements (i.e. dietary biomarkers). Dietary and serum biomarker measurements of B-vitamins from two nested case-control studies within the EPIC study were integrated in a Bayesian model to explore the measurement error structure of the data, and relate dietary exposures to risk of site-specific cancer.
A Bayesian hierarchical model was developed, which included 1) an exposure model, to define the distribution of unknown true exposure (T); 2) a measurement model, to relate observed assessments, in turn, dietary questionnaires (Q), 24-hour recalls (R) and biomarkers (M) to T measurements; 3) a disease model, to estimate exposures/cancer relationship. The marginal posterior distribution is obtained from the joint posterior distribution using MCMC sampling techniques in JAGS.
The study included 554 and 882 case/control pairs for kidney and lung cancer, respectively. After adjustment, T estimates were inversely related to kidney and lung cancer risk, with parameter estimates for T intakes consistently lower than Q and M measurements. Bayesian models offer very powerful solutions to handle complex data structures.


Visit the website: https://www.unige.ch/gsem/en/research/seminars/rcs/