Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · bayes-an/9510001

Bayesian Variable Selection with Related Predictors

Hugh Chipman
View original source ↗Read source document ↗Export metadata ↓

Abstract

In data sets with many predictors, algorithms for identifying a good subset of predictors are often used. Most such algorithms do not account for any relationships between predictors. For example, stepwise regression might select a model containing an interaction AB but neither main effect A or B. This paper develops mathematical representations of this and other relations between predictors, which may then be incorporated in a model selection procedure. A Bayesian approach that goes beyond the standard independence prior for variable selection is adopted, and preference for certain models is interpreted as prior information. Priors relevant to arbitrary interactions and polynomials, dummy variables for categorical factors, competing predictors, and restrictions on the size of the models are developed. Since the relations developed are for priors, they may be incorporated in any Bayesian variable selection algorithm for any type of linear model. The application of the methods here is illustrated via the Stochastic Search Variable Selection algorithm of George and McCulloch (1993), which is modified to utilize the new priors. The performance of the approach is illustrated with two constructed examples and a computer performance dataset. Keywords: Model Selection, Prior Distributions, Interaction, Dummy Variable

Explore related subjects

bayes-anphysics.data-an

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Hugh Chipman. 1995-10-31. Bayesian Variable Selection with Related Predictors. https://arxiv.org/abs/bayes-an/9510001

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv1996

Local computation of influence propagation through Bayes linear belief networks

In recent years there has been interest in the theory of local computation over probabilistic Bayesian graphical models. In this paper, local computation over Bayes linear belief networks is shown to be amenable to a similar approach. However, the linear structure offers many simplifications and advantages relative to more complex models, and these are examined with reference to some illustrative examples.

bayes-an↗
arXiv1996

Bayes linear variance adjustment for time series

This paper exhibits quadratic products of linear combinations of observables which identify the covariance structure underlying the univariate locally linear time series dynamic linear model. The first- and second-order moments for the joint distribution over these observables are given, allowing Bayes linear learning for the underlying covariance structure for the time series model. An example is given which illustrates the methodology and highlights the practical implications of the theory.

bayes-an↗
arXiv1996

Toward general solutions to time-series problems: Notes on obstacles and noise

Computational difficulties in the general application of Bretthorsts formalism to time-series problems, posed by the large number of possible models and the use of models with nonorthogonal base-functions are discussed. The specific problem under consideration is a Bayesian procedure for model selection, parameter estimation, and classification, that was applied to the search for the {\it {In Vivo}} $T_2$ decay rate distributions in brain tissues. Through the estimation of the meta-parameter $σ$ in the process, we also gain a better understanding of the meaning and estimation of "noise" in the frame-work of probability theory as logic.

bayes-an↗