On the safe use of prior densities for Bayesian model selection

Abstract

The application of Bayesian inference for the purpose of model selection is very popular nowadays. In this framework, models are compared through their marginal likelihoods, or their quotients, called Bayes factors. However, marginal likelihoods depend on the prior choice. For model selection, even diffuse priors can be actually very informative, unlike for the parameter estimation problem. Furthermore, when the prior is improper, the marginal likelihood of the corresponding model is undetermined. In this work, we discuss the issue of prior sensitivity of the marginal likelihood and its role in model selection. We also comment on the use of uninformative priors, which are very common choices in practice. Several practical suggestions are discussed and many possible solutions, proposed in the literature, to design objective priors for model selection are described. Some of them also allow the use of improper priors. The connection between the marginal likelihood approach and the well‐known information criteria is also presented. We describe the main issues and possible solutions by illustrative numerical examples, providing also some related code. One of them involving a real‐world application on exoplanet detection. This article is categorized under: Statistical Models > Bayesian Models Statistical Models > Fitting Models Statistical Models > Model Selection

Marketing Strategy of Private Enterprises Based on Bayesian Dynamic Panel Model of Machine Learning Algorithms

“…At the same time, it is also widely used in competitive strategy analysis, especially global strategy analysis, and it can also make a more effective and feasible analysis of the competitive environment. Porter's model contains some different factors in a simple model, which can be used to analyze the basic competitive situation of the industry (Llorente et al, 2023). Porter's model corresponds to five main sources of competition, namely, the bargaining power of suppliers, bargaining power of buyers, threat of new entrants, threat of substitutes, and degree of competition of competitors in the same industry (Wang et al, 2023).…”

Sparse Bayesian Estimation of Parameters in Linear-Gaussian State-Space Models

“…There are several approaches to estimate model parameters such that sparsity may be present. One approach may be to construct many models with unique combinations of sparse and dense elements, fit all of these models, and then select the best model according to some criteria (see [43], [44], [45] for examples). This approach is conceptually sound, but computationally expensive for even a small number of parameters p, as 2 p models must be fitted in order to obtain likelihood estimates, or other goodness-of-fit metrics.…”

“…As this holds for all models, it follows that p(M ) ∝ 1, and as the model space is discrete and finite, we can obtain an explicit value for the prior. Note that a diffuse prior is, in general, not allowed on the model space if using a posteriori model comparison methods [44]. However a diffuse prior is standard for RJMCMC [24], [26], [27], as the model space is sampled, and the model dynamically assessed alongside the parameter.…”

Mixture Modeling of Time-to-Event Data in the Proportional Odds Model

“…where n is the sample size and q is the dimension of β m . Note that this is strictly related to the marginal likelihood computation as can be seen in [27][28][29].…”