Learn More
Centre interuniversitaire de recherche en analyse des organisations (CIRANO), and Centre interuniversitaire de recherche en économie quantitative (CIREQ). ABSTRACT This paper considers the issue of testing hypotheses in the presence of (possibly) singular covariance matrices. We focus on the case where the finite-sample covariance matrix may not be singular(More)
In this paper we consider a discretely sampled Jacobi process appropriate to specify the dynamics of a process with range [0,1], such as a discount coefficient, a regime probability, or a state price. The discrete time transition of the Jacobi process does not admit a closed form expression and therefore the exact maximum likelihood is unfeasable. We first(More)
This paper examines Wald-type tests in presence of (possibly) singular covariance matrices. Two different types of singularity are addressed: first, the sample matrix has full rank but converges to a singular covariance matrix; in this case, the Wald statistic is still computable, but usual regularity conditions do not hold anymore, which modifies its(More)
The aim of this paper is to provide exact inference in nite sample for econometric models whose likelihood function is intractable and require thereby simulation-based estimation method like Indirect Inference Method or EEcient Method of Moments. To do so, we resort to the technique of Monte Carlo Tests which naturally applies to any simulable model. In(More)
  • 1