A large sample approximation of the posterior distribution of partially identified structural parameters is derived for models that can be indexed by a finite-dimensional reduced form parameter vector. It is used to analyze the differences between frequentist confidence sets and Bayesian...

This paper develops the asymptotic theory for stable autoregressive models in which the noise variance grows in a polynomial-like fashion. It is shown that the asymptotic distribution of the OLS estimator of the coefficient vector is multivariate normal with a covariance matrix that depends on...

In this paper we perform inference on the effect of a treatment on survival times in studies where the treatment assignment is not randomized and the assignment time is not known in advance. Two such studies are discussed: a heart transplant program and a study of Swedish unemployed eligible for...

Congratulations goes to Jon Wakefield for an unusually complete and completely insightful contribution to this fast-growing literature. Wakefield productively follows what is now standard practice by including both deterministic and statistical information in each new model and then seeking out...

The aim of this project was to improve the availability of information about coal quality parameters. Signals from existing instrumentation were evaluated in soft sensors and particle size sensors were further developed. The investigation of part products of the preparation process gave valuable...

Market definition is conducted under conditions of notable uncertainty, due to conceptual ambiguity and model uncertainty. Statistical decision theory can help to explain and improve the market definition decision. Specifically, a Bayesian decision rule can assist analysts in defining markets by...