In practice, the unknown parameters are often restricted. This paper provides a general method for constructing the fiducial intervals of the restricted parameters. Applying the general method, the fiducial intervals ...In practice, the unknown parameters are often restricted. This paper provides a general method for constructing the fiducial intervals of the restricted parameters. Applying the general method, the fiducial intervals are constructed for the location (scale)parameters and the difference (ratio) of two locations (scales) in a location (scale) family of distributions. The frequency properties of these intervals are verified. For a variance components model, the fiducial intervals for the three parameters of common interest are obtained. Their frequency properties are investigated theoretically and computationally.展开更多
Bayes decision rule of variance components for one-way random effects model is derived and empirical Bayes (EB) decision rules are constructed by kernel estimation method. Under suitable conditions, it is shown that t...Bayes decision rule of variance components for one-way random effects model is derived and empirical Bayes (EB) decision rules are constructed by kernel estimation method. Under suitable conditions, it is shown that the proposed EB decision rules are asymptotically optimal with convergence rates near O(n-1/2). Finally, an example concerning the main result is given.展开更多
基金supported by Natural Natural Science Foundation of China(Grant Nos.10271013,19631040&10371126).
文摘In practice, the unknown parameters are often restricted. This paper provides a general method for constructing the fiducial intervals of the restricted parameters. Applying the general method, the fiducial intervals are constructed for the location (scale)parameters and the difference (ratio) of two locations (scales) in a location (scale) family of distributions. The frequency properties of these intervals are verified. For a variance components model, the fiducial intervals for the three parameters of common interest are obtained. Their frequency properties are investigated theoretically and computationally.
基金The project is partly supported by NSFC (19971085)the Doctoral Program Foundation of the Institute of High Education and the Special Foundation of Chinese Academy of Sciences.
文摘Bayes decision rule of variance components for one-way random effects model is derived and empirical Bayes (EB) decision rules are constructed by kernel estimation method. Under suitable conditions, it is shown that the proposed EB decision rules are asymptotically optimal with convergence rates near O(n-1/2). Finally, an example concerning the main result is given.
