Legend: Palais des congrès de Montréal = CC, Le Westin Montréal = W, Intercontinental Montréal = I
A * preceding a session name means that the session is an applied session.
A ! preceding a session name means that the session reflects the JSM meeting theme.
A * preceding a session name means that the session is an applied session.
A ! preceding a session name means that the session reflects the JSM meeting theme.
Activity Details
|
|
Tweet | ||
| CE_04C | Sat, 8/3/2013, 8:30 AM - 5:00 PM | W-St. Antoine | |
| Bayesian Model Specification: Toward a Theory of Applied Statistics — Continuing Education Course | |||
| ASA , Section on Bayesian Statistical Science | |||
| Instructor(s): David Draper, University of California, Santa Cruz | |||
| Bayesian models are supposed to arise from problem context, but context rarely specifies the model uniquely; how do we cope well with model uncertainty? As a profession we have a series of ad-hoc suggestions for how to specify models well, but we have no natural progression from principles to axioms to theorems on optimal Bayesian model specification. Developing such a progression could be referred to as creating a Theory of Applied Statistics, which we need but do not yet have. In this short course I will (a) define optimal Bayesian model specification, (b) lay out a number of principles that are helpful in moving toward the goal in (a), and (c) examine a variety of methods --- for Bayesian model comparison, choice and evaluation --- that arise from the principles in (b). I'll do these things in the context of a series of real-world case studies; data sets and R code to carry out all calculations will be provided for the participants on the short course web page. The target audience is students and professionals with good statistical preparation and some working knowledge of Bayesian reasoning; a solid calculus-based probability background is necessary to gain full appreciation of the material presented. This is essentially a second Bayesian course, following on from a good first course on introductory topics. | |||
2013 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.