传统的测量不确定评定是A类、B类评定,与这两类评定方法不同,提出了一种基于贝叶斯理论的测量不确定度评定方法。此方法综合了历史信息和当前样本信息,通过建立贝叶斯模型得出后验分布,从而进行测量不确定度评定。通过实例说明,贝叶斯评定比A类评定更为合理。
The traditional evaluation of uncertainty in measurement is type A and type B evaluation, a new method for evaluation of uncertainty in measurement based on Bayesian theory are proposed which is different from the two evalution methods. In order to obtain posterior distribution this method combines historical information and the current sample information through the establishment of the Bayesian model , so the evaluation of uncertainty in measurement can be carried out. Bayesian evaluation is more reasonable than type A evaluation with the examole.