Semiparametric Estimation of a Bivariate Gamma Degradation Model
The gamma process is one of the widely used models for analyzing mono-tonic degradation data.Parametric estimation of the gamma process-based degra-dation models requires one to postulate specific forms for shape functions.However,there may sometimes be no enough information to determine appropriate functional forms,which makes the parametric estimation method inapplicable.Regarding the bivariate gamma degradation model proposed by Song and Cui(2022),this paper in-vestigates the problem of estimating shape functions nonparametrically.An efficient estimation procedure is developed based on the expectation maximization algorithm.Numerical simulations are performed,and the results demonstrate the effectiveness of the proposed method.Finally,a real data set is analyzed for illustration.
Expectation maximization algorithmGamma processnonparametric estimationreliabilityshape function
NETL
NSTL
万方数据
