A0160
Title: Subsampling strategies for heavily censored reliability big data
Authors: Qingpei Hu - Academy of Mathematics and Systems Science, Chinese Academy of Sciences (China) [presenting]
Abstract: While subsampling techniques have been extensively developed in the literature to downsize the data volume, there is a notable gap in addressing the unique challenge of handling extensive reliability data, in which a common situation is that a large proportion of data is censored. A subsampling method is proposed for reliability analysis in the presence of censoring data to estimate the parameters of lifetime distribution effectively and efficiently. The asymptotic properties of the subsampling-based estimators are given, and the optimal subsampling probabilities are derived by minimizing the criterion defined by the trace of the asymptotic covariance matrix. Efficient algorithms are proposed to implement the proposed subsampling methods to address the challenge of the optimal subsampling strategy depending on unknown parameter estimation from full data. Numerical studies and a real-world dataset are employed to illustrate the performance of the proposed methods. The results demonstrate the superior performance of the proposed methods compared to uniform subsampling and the effective alleviation of the computational burden compared with the computational time of full data analysis.
