Browse > Article
http://dx.doi.org/10.3795/KSME-A.2015.39.2.163

Threshold Estimation of Generalized Pareto Distribution Based on Akaike Information Criterion for Accurate Reliability Analysis  

Kang, Seunghoon (Dept. of Automotive Engineering, Graduate School, Hanyang Univ.)
Lim, Woochul (Dept. of Automotive Engineering, Graduate School, Hanyang Univ.)
Cho, Su-Gil (Dept. of Automotive Engineering, Graduate School, Hanyang Univ.)
Park, Sanghyun (Dept. of Automotive Engineering, Graduate School, Hanyang Univ.)
Lee, Minuk (Technology Center for Offshore Plant Industries, Korea Research Institute of Ships and Ocean Engineering)
Choi, Jong-Su (Offshore Plant Research Division, Korea Research Institute of Ships and Ocean Engineering)
Hong, Sup (Technology Center for Offshore Plant Industries, Korea Research Institute of Ships and Ocean Engineering)
Lee, Tae Hee (Dept. of Automotive Engineering, Graduate School, Hanyang Univ.)
Publication Information
Transactions of the Korean Society of Mechanical Engineers A / v.39, no.2, 2015 , pp. 163-168 More about this Journal
Abstract
In order to perform estimations with high reliability, it is necessary to deal with the tail part of the cumulative distribution function (CDF) in greater detail compared to an overall CDF. The use of a generalized Pareto distribution (GPD) to model the tail part of a CDF is receiving more research attention with the goal of performing estimations with high reliability. Current studies on GPDs focus on ways to determine the appropriate number of sample points and their parameters. However, even if a proper estimation is made, it can be inaccurate as a result of an incorrect threshold value. Therefore, in this paper, a GPD based on the Akaike information criterion (AIC) is proposed to improve the accuracy of the tail model. The proposed method determines an accurate threshold value using the AIC with the overall samples before estimating the GPD over the threshold. To validate the accuracy of the method, its reliability is compared with that obtained using a general GPD model with an empirical CDF.
Keywords
Generalized Pareto Distribution; Threshold; Akaike Information Criterion; Tail Model; Reliability Analysis;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Breitung, K., 1984, "Asymptotic Approximation for Multinormal Integrals," Journal of Engineering Mechanics, Vol. 110, No. 3, pp. 357-366.   DOI   ScienceOn
2 Cornell, C. A., 1969, "A Probability-based Structural Code," Journal of the American Concrete Institute, Vol. 66, No. 12, pp. 974-985.
3 Cho, S, Lee, M., Lim, W., Choi, J. S., Kim, H. W., Hong, S. and Lee, T. H., 2012, "Efficient Robust Design Optimization Using Statistical Moment Based on Multiplicative Decomposition Considering Nonnormal Noise Factors," Trans. Korean Soc. Mech. Eng. A, Vol. 36, No. 11, pp. 1305-1310.   DOI   ScienceOn
4 Jung, J. J., 2007, "Multiplication Decomposition Method for Accurate Moment-Based Reliability Analysis," Ph.D. thesis, Hanyang University.
5 Lim, W. and Lee, T. H., 2010, "Reliability-based Design Optimization using Akaike Information Criterion for Discrete Information," Trans. Korean Soc. Mech. Eng. A, Vol. 36, No. 8, pp. 568-573.
6 Kim, N. H. and Ramu, P., 2006, "Tail Modeling in Reliability-Based Design Optimization for Highly Safe Structural Systems," 47th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference.
7 De Zea Bermudez, P. and Kotz, S., 2010, "Parameter Estimation of The Generalized Pareto Distribution-Part 1," Journal of Statistical Planning and Inference, Vol. 140, No. 6, pp. 1353-1373.   DOI   ScienceOn
8 McNeil, A. J. and Frey, R., 2000, "Estimation of Tail-Related Risk Measures for Heteroscedastic Financial Time Series: An Extreme Value Approach," Journal of Empirical finance, Vol. 7, No. 3, pp. 271-300.   DOI   ScienceOn
9 Begueria, S., 2005, "Uncertainties in Partial Duration Series Modeling of Extremes Related to The Choice of The Threshold Value," Journal of Hydrology, Vol. 303, No. 1, pp. 215-230.   DOI   ScienceOn
10 Boos, D. D., 1984, "Using Extreme Value Theory to Estimate Large Percentiles," Technometrics, Vol.26, No.1, pp. 33-39.   DOI   ScienceOn
11 Hasofer, A. M., 1996, "Non-parametric Estimation of Failure Probabilities," Mathematical Models for Structural Reliability Analysis. Edited by Casicati, F. and Roberts, B., CRC Press.
12 Pickands, J., 1975, "Statistical Inference using Extreme Order Statistics," The Annals of Statistics, Vol. 3, No. 1, pp. 119-131.   DOI