If you need an accessible version of this item please contact JSTOR User Support

Model Selection and Accounting for Model Uncertainty in Graphical Models Using Occam's Window

David Madigan and Adrian E. Raftery
Journal of the American Statistical Association
Vol. 89, No. 428 (Dec., 1994), pp. 1535-1546
DOI: 10.2307/2291017
Stable URL: http://www.jstor.org/stable/2291017
Page Count: 12
  • Download PDF
  • Cite this Item

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

If you need an accessible version of this item please contact JSTOR User Support
Model Selection and Accounting for Model Uncertainty in Graphical Models Using Occam's Window
Preview not available

Abstract

We consider the problem of model selection and accounting for model uncertainty in high-dimensional contingency tables, motivated by expert system applications. The approach most used currently is a stepwise strategy guided by tests based on approximate asymptotic P values leading to the selection of a single model; inference is then conditional on the selected model. The sampling properties of such a strategy are complex, and the failure to take account of model uncertainty leads to underestimation of uncertainty about quantities of interest. In principle, a panacea is provided by the standard Bayesian formalism that averages the posterior distributions of the quantity of interest under each of the models, weighted by their posterior model probabilities. Furthermore, this approach is optimal in the sense of maximizing predictive ability. But this has not been used in practice, because computing the posterior model probabilities is hard and the number of models is very large (often greater than 1011). We argue that the standard Bayesian formalism is unsatisfactory and propose an alternative Bayesian approach that, we contend, takes full account of the true model uncertainty by averaging over a much smaller set of models. An efficient search algorithm is developed for finding these models. We consider two classes of graphical models that arise in expert systems: the recursive causal models and the decomposable log-linear models. For each of these, we develop efficient ways of computing exact Bayes factors and hence posterior model probabilities. For the decomposable log-linear models, this is based on properties of chordal graphs and hyper-Markov prior distributions and the resultant calculations can be carried out locally. The end product is an overall strategy for model selection and accounting for model uncertainty that searches efficiently through the very large classes of models involved. Three examples are given. The first two concern data sets that have been analyzed by several authors in the context of model selection. The third addresses a urological diagnostic problem. In each example, our model averaging approach provides better out-of-sample predictive performance than any single model that might reasonably have been selected.

Page Thumbnails

  • Thumbnail: Page 
1535
    1535
  • Thumbnail: Page 
1536
    1536
  • Thumbnail: Page 
1537
    1537
  • Thumbnail: Page 
1538
    1538
  • Thumbnail: Page 
1539
    1539
  • Thumbnail: Page 
1540
    1540
  • Thumbnail: Page 
1541
    1541
  • Thumbnail: Page 
1542
    1542
  • Thumbnail: Page 
1543
    1543
  • Thumbnail: Page 
1544
    1544
  • Thumbnail: Page 
1545
    1545
  • Thumbnail: Page 
1546
    1546