Wiener processes with random effects for degradation data. (English) Zbl 1178.62091

Summary: This article studies the maximum likelihood inference of a class of Wiener processes with random effects for degradation data. Degradation data are a special case of functional data with monotone trend. The setting for degradation data is one on which n independent subjects, each with a Wiener process with random drift and diffusion parameters, are observed at possible different times. Unit-to-unit variability is incorporated into the model by these random effects. The EM algorithm is used to obtain the maximum likelihood estimators of the unknown parameters. Asymptotic properties such as consistency and convergence rate are established. The bootstrap method is used for assessing the uncertainties of the estimators. Simulations are used to validate the method. The model is fitted to bridge beam data and corresponding goodness-of-fit tests are carried out. Failure time distributions in terms of degradation level passages are calculated and illustrated.


62M05 Markov processes: estimation; hidden Markov models
62N05 Reliability and life testing
62F12 Asymptotic properties of parametric estimators
62N02 Estimation in survival analysis and censored data
62G20 Asymptotic properties of nonparametric inference
65C60 Computational problems in statistics (MSC2010)


bootstrap; SPLIDA
Full Text: DOI


[1] DeGruttola, V.; Lange, N.; Dafni, U., Modeling the progression of HIV infection, Journal of the American Statistical Association, 86, 569-577 (1991)
[3] Lu, C. J.; Meeker, W. Q., Using degradation measures to estimate a time-to-failure distribution, Technometrics, 35, 161-171 (1993) · Zbl 0775.62271
[4] Elsayed, E. A.; Liao, H. T., A geometric Brownian motion model for field degradation data, International Journal Materials and Product Technology, 20, 51-72 (2004)
[5] Singpurwalla, N. D., Survival in dynamic environments, Statistical Science, 1, 86-103 (1995) · Zbl 1148.62314
[6] Meeker, W. Q.; Escobar, L. A., Statistical Methods for Reliability Data (1998), Wiley: Wiley New York · Zbl 0949.62086
[7] Wang, X., Physical degradation models, (Ruggeri, F.; Kenett, R.; Faltin, F. W., Encyclopedia of Statistics in Quality and Reliability (2007), John Wiley & Sons Lts: John Wiley & Sons Lts Chichester, UK), 1356-1361
[8] Doksum, K., Degradation rate models for failure time and survival data, CWI Quarterly, 195-203 (1991) · Zbl 0762.62032
[9] Doksum, K.; Hoyland, A., Models for variable stress accelerated life testing experiments based on wiener process and the inverse gaussian distribution, Technometrics, 34, 74-82 (1992) · Zbl 0763.62048
[10] Whitmore, G. A., Estimation degradation by a Wiener diffusion process subject to measurement error, Lifetime Data Analysis, 1, 307-319 (1995) · Zbl 0960.62540
[11] Whitmore, G. A.; Schenkelberg, F., Modelling accelerated degradation data using Wiener diffusion with a time scale transformation, Lifetime Data Analysis, 3, 27-43 (1997) · Zbl 0891.62071
[12] Chikkara, R. S.; Folks, J. L., The Inverse Gaussian Distribution (1989), Marcell Dekker: Marcell Dekker NY
[13] Sheshadri, V., The Inverse Gaussian Distribution (1998), Springer: Springer NY
[15] Chaloner, K.; Verdinelli, I., Bayesian experimental design: A review, Statistical Science, 10, 273-304 (1995) · Zbl 0955.62617
[16] Lawless, J.; Crowder, M., Covariate and random effects in a Gamma process model with application to degradation and failure, Lifetime Data Analysis, 10, 213-227 (2004) · Zbl 1054.62122
[17] Little, R. J.A.; Rubin, D. B., Statistical Analysis with Missing Data (1987), John Wiley: John Wiley New York · Zbl 0665.62004
[18] Little, R. J.A., Robust estimation of the mean and covariance matrix from data with missing values, Applied Statistics, 37, 23-38 (1988) · Zbl 0647.62040
[19] Lange, K. L.; Little, R. J.A.; Taylor, J. M.G., Robust statistical modeling using the \(t\) distribution, Journal of the American Statistical Association, 84, 881-896 (1989)
[20] Liu, C.; Rubin, D. B., ML estimation of the multivariate \(t\) distribution with unknown degrees of freedom, Statistica Sinica, 5, 19-39 (1995)
[21] Liu, C., ML estimation of the multivariate \(t\) distribution and the EM algorithm, Journal of Multivariate Analysis, 63, 296-312 (1997) · Zbl 0884.62059
[22] Bertsekas, D. P., Nonlinear Programming (2003), Athena Scientific · Zbl 0935.90037
[23] Wellner, J.; Zhang, Y., Two estimators of the mean of a counting process with panel count, The Annals of Statistics, 28, 779-814 (2000) · Zbl 1105.62372
[24] Wellner, J.; Zhang, Y., Two likelihood-based semiparametric estimation methods for panel data with covariates, The Annals of Statistics, 35, 2106-2142 (2007) · Zbl 1126.62084
[25] Efron, B.; Tibshirani, R., An Introduction to Bootstrap (1993), Chapman & Hall/CRC · Zbl 0835.62038
[26] Efron, B., Nonparametric standard errors and confidence intervals (with discussion), Canadian Journal of Statistics, 9, 139-172 (1981) · Zbl 0482.62034
[27] Efron, B., The Jackknife, the Bootstrap, and Other Resampling Plans (1982), SIAM: SIAM Philadelphia · Zbl 0496.62036
[28] Bagdonavicius, V.; Nikulin, M., Estimation in degradation models with explanatory variables, Lifetime Data Analysis, 7, 85-103 (2000) · Zbl 1010.62094
[29] Vaart, van der; Wellner, J., (Weak Convergence and Empirical Processes with Applications to Statistics. Weak Convergence and Empirical Processes with Applications to Statistics, Springer Series in Statistics (1996)) · Zbl 0862.60002
[30] Vaart, van der, Semiparametric statistics, (Lectures on Probability Theory and Statistics. Lectures on Probability Theory and Statistics, Lecture Notes in Mathematics, vol. 1781 (2002)), 330-457 · Zbl 1013.62031
[31] Jorgensen, B., Statistical Properties of the Generalized Inverse Gaussian Distribution (1982), Springer-Verlag: Springer-Verlag New York · Zbl 0486.62022
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.