The Bernstein-Von-Mises theorem under misspecification
By Kleijn, Van der Vaart. 2012
313 citations recorded by the source corpus.
We prove that the posterior distribution of a parameter in misspecified LAN parametric models can be approximated by a random normal distribution. We derive from this that Bayesian credible sets are not valid confidence sets if the model is misspecified. We obtain the result under conditions that are comparable to those in the well-specified situation: uniform testability against fixed alternatives and sufficient prior mass in neighbourhoods of the point of convergence. The rate of convergence is considered in detail, with special attention for the existence and construction of suitable test sequences. We also give a lemma to exclude testable model subsets which implies a misspecified version of Schwartz’ consistency theorem, establishing weak convergence of the posterior to a measure degenerate at the point at minimal Kullback-Leibler divergence with respect to the true distribution.
Subfields: Computational Theory and Mathematics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Theory and Mathematics
Citations in the corpus
- Robust generalised Bayesian inference for intractable likelihoods (2021, unknown): “…Theorem 2 differs to the precision matrix H ∗ J − 1 ∗ H ∗ of the minimum KSD estimator from Lemma 4; this is analogous to fact that Bayesian credible sets can have asymptotically incorrect frequentist coverage if the statistical model is misspecified (Kleijn & van der Vaart, 2012; Müller, 2013).”
- Critical dimension in the semiparametric Bernstein—von Mises theorem (2014, background): “Under model misspecification, υ∗ defines the best parametric fit to P by the considered family (see [11, 19, 20] and references therein).”