Estimating failure time distribution and its parameters based on intermediate data from a Wiener degradation model. (English) Zbl 1210.90068

Tang, Jen; Su, Tsui-Shu

Nav. Res. Logist. 55, No. 3, 265-276 (2008).

Summary: Instead of measuring a Wiener degradation or performance process at predetermined time points to track degradation or performance of a product for estimating its lifetime, we propose to obtain the first-passage times of the process over certain nonfailure thresholds. Based on only these intermediate data, we obtain the uniformly minimum variance unbiased estimator and uniformly most accurate confidence interval for the mean lifetime. For estimating the lifetime distribution function, we propose a modified maximum likelihood estimator and a new estimator and prove that, by increasing the sample size of the intermediate data, these estimators and the above-mentioned estimator of the mean lifetime can achieve the same levels of accuracy as the estimators assuming one has failure times. Thus, our method of using only intermediate data is useful for highly reliable products when their failure times are difficult to obtain. Furthermore, we show that the proposed new estimator of the lifetime distribution function is more accurate than the standard and modified maximum likelihood estimators. We also obtain approximate confidence intervals for the lifetime distribution function and its percentiles. Finally, we use light-emitting diodes as an example to illustrate our method and demonstrate how to validate the Wiener assumption during the testing.

MSC:

90B25	Reliability, availability, maintenance, inspection in operations research
62N05	Reliability and life testing

Keywords:

degradation process; performance process; Wiener process; inverse Gaussian distribution; lifetime or failure time distribution; percentiles; maximum likelihood estimator; uniformly minimum variance unbiased estimator; goodness-of-fit test

References:

[1]	Banerjee, J Amer Statist Assoc 71 pp 823– (1976)
[2]	, The inverse Gaussian distribution: theory, methodology, and applications, Marcel Dekker, New York, 1989.
[3]	Estimating time-to-failure distribution and its parameters based on initial Wiener degradation data for highly reliable products, National Tsing-Hua University, Taiwan, MS thesis, 2003.
[4]	Cox, Lifetime Data Anal 5 pp 307– (1999)
[5]	Doksum, Technometrics 34 pp 74– (1992)
[6]	Doksum, Lifetime Data Anal 1 pp 131– (1995)
[7]	Ebrahimi, Naval Res Logistics 52 pp 46– (2005)
[8]	Gebraeel, IIE Trans 37 pp 543– (2005)
[9]	Hasofer, Proc Camb Phil Soc 60 pp 931– (1964)
[10]	Iwase, J Am Statist Assoc 78 pp 660– (1983)
[11]	Lancaster, J R Statist Soc A 135 pp 257– (1972)
[12]	, Theory of point estimation, Springer-Verlag, New York, 1998.
[13]	Liao, Naval Res Logist 53 pp 576– (2006)
[14]	Lee, J R Statist Soc Ser B Statist Method 62 pp 747– (2000)
[15]	Lu, Technometrics 35 pp 161– (1993)
[16]	, Statistical methods for reliability data, Wiley, New York, 1998. · Zbl 0949.62086
[17]	Accelerated testing: Statistical models, test plans, and data analysis, Wiley, New York, 1990.
[18]	Pavur, IEEE Trans on Reliab R-41 pp 118– (1992)
[19]	The inverse Gaussian distribution: statistical theory and applications, Springer-Verlag, New York, 1999.
[20]	Basic principles of the tracer method, Wiley, New York, 1962.
[21]	Singpurwalla, IMS Lect Notes-Monogr Ser, 2nd Lehmann Symp 49 pp 229– (2006)
[22]	Srivastava, Ann Statist 21 pp 645– (1993)
[23]	Tang, IEEE Trans on Reliab R-44 pp 562– (1995)
[24]	Tseng, Naval Res Logist 50 pp 1– (2003)
[25]	Tseng, IEEE Trans Reliab R-46 pp 130– (1997)
[26]	Tweedie, Ann Math Statist 28 pp 362– (1957)
[27]	Whitmore, Lifetime Data Anal 4 pp 229– (1998)
[28]	Whitmore, Lifetime Data Anal 3 pp 27– (1997)
[29]	Zhao, IEEE Proc RAMS, CA pp 324– (2004)