Empirical Bayes Decision for a Generalized Exponential Distribution with Contaminated Data

The two-sided and one-sided empirical Bayes test (EBT) rules for the parameter of a generalized exponential distribution with contaminated data (errors in variables) are constructed by deconvolution kernel method, respectively. Under type supersmooth error distributions errors level can be controlled situations, asymptotically optimal uniformly over class prior uniform rates convergence corresponding regret proposed EBT obtained suitable conditions. example study shows that assumptions conditions main results this paper satisfied easily calculating.