Statistical Degradation Data Analysis
Description
This book provides a systematic treatment of efficient methods for modeling, analyzing, and designing degradation tests, with particular emphasis on stochastic-process-based semiparametric and nonparametric approaches motivated by practical applications.
Statistical Degradation Data Analysis: Semiparametric and Nonparametric Stochastic Process Approaches compares parametric, semiparametric, and nonparametric methods through Monte Carlo simulation studies and real data examples, and demonstrates how these methodologies can be applied across a range of disciplines. The book also discusses extensions and open problems in this area.
In engineering and the sciences, degradation refers to the gradual and irreversible decline in the performance, reliability, or remaining life of a system or asset. Because many systems are equipped with sensors that collect degradation measurements over time, statistical degradation modeling plays an important role in understanding the evolution of such processes and supporting reliability assessment.
A common approach to degradation data analysis is stochastic process modeling. Classical models such as the Wiener, gamma, and inverse Gaussian processes have been widely studied and applied. However, these parametric models require specific assumptions on the distributions of degradation increments and may perform poorly when those assumptions are violated. To address this limitation, semiparametric and nonparametric methods, which rely on fewer distributional assumptions, can provide more robust and reliable alternatives.
This book is intended for senior undergraduates, graduate students, researchers, and practitioners. It can also serve as a reference for courses in lifetime data analysis or reliability engineering. Computer programs for numerical examples are provided to facilitate replication and practical implementation.
More details
Persons
Hon Keung Tony Ng is a Professor in the Department of Mathematical Sciences at Bentley University (Waltham, MA, USA). He is Co-Editor of Communications in Statistics-Simulation and Computation and serves as Associate Editor for IEEE Transactions on Reliability , Naval Research Logistics , Sequential Analysis , and Statistics & Probability Letters . His research interests include reliability, censoring methodology, degradation modeling, ordered data analysis, nonparametric methods, and statistical inference. He has published over 200 refereed papers and co-authored Precedence-Type Tests and Applications (Wiley, 2006) and Fiber Bundles: Statistical Models and Applications (Springer, 2023). He has also co-edited the books Ordered Data Analysis, Modeling and Health Research Methods ; Statistical Modeling for Degradation Data ; Statistical Quality Technologies: Theory and Practice ; Bayesian Inference and Computation in Reliability and Survival Analysis; and Recent Advances on Sampling Methods and Educational Statistics . He is a Senior Member of IEEE, an elected member of the International Statistical Institute, a Fellow of the American Statistical Association, and a Senior Member of the American Society for Quality.
Lochana Palayangoda is an Assistant Professor in the Department of Mathematical and Statistical Sciences at the University of Nebraska Omaha. Before joining academia, he worked as an R&D Senior Data Scientist at PepsiCo, Inc., a visiting scholar at the Lighting Research Center at Rensselaer Polytechnic Institute, and as an Electrical Engineer in Sri Lanka. He is also a research member of the Nebraska Education Policy Research Lab. His research interests include degradation data modeling, synthetic data generation, sports statistics, and education data analysis.
Content
Chapter 1 Introduction and Preliminaries.- Chapter 2 Linear Univariate Degradation Data.- Chapter 3 Nonlinear Univariate Degradation Data.- Chapter 4 Bivariate Degradation Data.- Chapter 5 Accelerated Degradation Testing.- Chapter 6 Optimal Designs of Degradation Test.- Chapter 7 Random Effect Models for Degradation Test Data.- Chapter 8 Goodness-of-Fit Test Procedures for Degradation Data.