Research on Measurement Uncertainty Evaluation Methods Based on Bayesian Principle
In current application of measurement uncertainty evaluation, dynamic uncertainty evaluation simply uses the static uncertainty methods. To change the situation, a new evaluation method of measurement uncertainty is investigated based on Bayesian principle in this paper. Bayesian evaluation method uses conjugate normal-inverted gamma distribution as the distribution function in uncertainty evaluation, which can be employed to evaluate both static and dynamic measurement uncertainty. The evaluation method put forward in this paper can achieve higher evaluation accuracy than the conventional methods, particularly in processing dynamic data with small samples. It has been proved in theory and by computer simulation.
Wei Gao, Yasuhiro Takaya, Yongsheng Gao and Michael Krystek
X. H. Chen et al., "Research on Measurement Uncertainty Evaluation Methods Based on Bayesian Principle", Key Engineering Materials, Vols. 381-382, pp. 583-586, 2008