2014/09/09 by Shota Gugushvili, Peter Spreij · 6 citations
Computer Science · Mathematics · #Applied mathematics #Bayesian probability #Contraction (grammar) #Contraction mapping #Gaussian Processes and Bayesian Inference #Large deviations theory #Mathematical analysis #Mathematical optimization #Mathematics #Parametric statistics #Rate function #Statistical Methods and Inference #Statistics #Stochastic differential equation #Target Tracking and Data Fusion in Sensor Networks #math.ST #msc:62G20 #msc:62M05 #stat.TH
paper · pdf · doi:10.1051/ps/2016008
published in ESAIM Probability and Statistics 20, 143-153 (EDP Sciences) · 11 pages
arxiv created 2014/09/09 · openalex publication_date 2016/01/01 · arxiv updated 2018/04/17 · openalex created_date 2020/11/23 · openalex updated_date 2026/08/05
We consider the problem of non-parametric estimation of the deterministic dispersion coefficient of a linear stochastic differential equation based on discrete time observations on its solution. We take a Bayesian approach to the problem and under suitable regularity assumptions derive the posteror contraction rate. This rate turns out to be the optimal posterior contraction rate.