Prior-free Bayes Factors Based on Data Splitting Academic Article uri icon

abstract

  • 2019 The Authors. International Statistical Review 2019 International Statistical Institute Bayes factors that do not require prior distributions are proposed for testing one parametric model versus another. These Bayes factors are relatively simple to compute, relying only on maximum likelihood estimates, and are Bayes consistent at an exponential rate for nested models even when the smaller model is true. These desirable properties derive from the use of data splitting. Large sample properties, including consistency, of the Bayes factors are derived, and a simulation study explores practical concerns. The methodology is illustrated with civil engineering data involving compressive strength of concrete.

published proceedings

  • INTERNATIONAL STATISTICAL REVIEW

author list (cited authors)

  • Hart, J. D., & Malloure, M.

citation count

  • 1

complete list of authors

  • Hart, Jeffrey D||Malloure, Matthew

publication date

  • January 2019

publisher