Dear all,
Please join us for the Applied Statistics Workshop (Gov 3009) this
Wednesday, February 22 from 12.00 - 1.30 pm in CGIS Knafel Room 354. Francesca
Dominici <http://www.hsph.harvard.edu/faculty/francesca-dominici/>,
Professor of Biostatistics at the Harvard School of Public Health, will
give a presentation entitled "Bayesian Effect Estimation Accounting for
Adjustment Uncertainty". As always, a light lunch will be provided.
Abstract:
Model-based estimation of the effect of an exposure on an outcome is
generally sensitive to the choice of which confounding
factors are included
in the model. We propose a new approach, which we call Bayesian Adjustment
for Confounding (BAC), to estimate the effect on the outcome associated
with an exposure of interest while accounting for the uncertainty in the
confounding adjustment. Our approach is based on specifying two models: 1)
the outcome as a function of the exposure and the potential confounders
(the outcome model); and 2) the exposure as a function of the potential
confounders (the exposure model). We consider Bayesian variable selection
on both models and link the two by introducing a dependence parameter ω
denoting the prior odds of including a predictor in the outcome model,
given that the same predictor is in the exposure model. In the absence of
dependence (ω = 1), BAC reduces to traditional Bayesian Model Averaging
(BMA). In simulation studies we show that BAC with ω > 1 estimates the
exposure effect with smaller bias than traditional BMA, and improved
coverage. We then compare BAC, a recent approach of Crainiceanu et al.
(2008), and traditional BMA in a time series data set of hospital
admissions, air pollution levels and weather variables in Nassau, NY for
the period 1999-2005. Using each approach, we estimate the short-term
effects of PM2.5 on emergency admissions for cardiovascular diseases,
accounting for confounding. This application illustrates the potentially
significant pitfalls of misusing variable selection methods in the context
of adjustment uncertainty.
An up-to-date schedule for the workshop is available at
http://www.iq.harvard.edu/events/node/1208.
Best,
Konstantin
--
Konstantin Kashin
Ph.D. Student in Government
Harvard University
Mobile: 978-844-0538
E-mail: kkashin(a)fas.harvard.edu
Site:
http://www.konstantinkashin.com/<http://people.fas.harvard.edu/%7Ekkashi…