Title :
Study on the influence of prior reliability for bayesian estimation
Author_Institution :
Coll. of Inf. Syst. & Manage., Nat. Univ. of Defense Technol., Changsha, China
Abstract :
Bayesian method has been widely used for parameters evaluation and decision making. However, existing studies paid more attention on the construction of prior distribution and method engineering applications. The previous researches had fewer discourses on the reliability influence analysis of prior information or prior distribution. In this paper, based on the coherence analysis between prior information and field test results, the definition of prior reliability was presented, and the calculation process based on hypothesis testing theory was given. For normal distribution, to a numerical example, the influence analysis result was exhibited. Furthermore, the interval estimation method considering the influence of prior reliability was given.
Keywords :
Bayes methods; decision making; estimation theory; normal distribution; reliability theory; statistical testing; Bayesian estimation; coherence analysis; decision making; hypothesis testing theory; interval estimation method; method engineering application; normal distribution; numerical example; parameter evaluation; prior distribution; prior information; prior reliability influence analysis; Bayesian methods; Decision making; Educational institutions; Gaussian distribution; Information analysis; Information management; Management information systems; Reliability engineering; Technology management; Testing; Bayesian method; Influence; Interval estimation; Prior Reliability;
Conference_Titel :
Reliability, Maintainability and Safety, 2009. ICRMS 2009. 8th International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-4903-3
Electronic_ISBN :
978-1-4244-4905-7
DOI :
10.1109/ICRMS.2009.5270160
