Sufficiency in decision processes with continuous observations
Statistical decision problems are considered in the case of continuous observations, i.e. each observation is a path of a continuous time stochastic process. Decisions are compared with respect to expected loss plus expected observation costs. Given the filtration \(F_ t\), \(t\geq 0\), of the process \((F_ t\) is the set of events up to time t), sufficiency is defined via sufficient subfields \(G_ t\) of \(F_ t\), for each \(t\geq 0\). It is shown that the class of all decision rules which are based on \(G_ t\)-observable events is essentially complete.
- scientific article; zbMATH DE number 3456238 (Why is no real title available?)
- scientific article; zbMATH DE number 3246773 (Why is no real title available?)
- scientific article; zbMATH DE number 3272022 (Why is no real title available?)
- Introduction to mathematical statistics. Translated from the German by Kenneth Wickwire
- Sufficiency and Statistical Decision Functions
- Sufficiency in sequentially planned decision procedures
- A decision procedure for von Wright's OBS-calculus
- Invariance in decision processes with continuous observations
- Completitud esencial de la clase de controles basados en un proceso suficiente
- scientific article; zbMATH DE number 4038993 (Why is no real title available?)
- scientific article; zbMATH DE number 1336737 (Why is no real title available?)
This page was built for publication: Sufficiency in decision processes with continuous observations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3470007)