Penultimate Approximations in Statistics of Extremes and Reliability of Large Coherent Systems

详细信息    查看全文

• 作者：Paula Reis (1) (2)
  Lu铆sa Canto e Castro (1) (3)
  Sandra Dias (4) (5)
  M. Ivette Gomes (1) (3) (6)
  
  1. CEAUL ; Lisboa ; Portugal
  2. DMAT ; EST-IPS ; Set煤bal ; Portugal
  3. DEIO ; FCUL ; Universidade de Lisboa ; Lisboa ; Portugal
  4. CM-UTAD ; Vila Real ; Portugal
  5. Universidade de Tr谩s-os-Montes e Alto Douro ; Vila Real ; Portugal
  6. DEIO ; Faculdade de Ci锚ncias da Universidade de Lisboa ; Campo Grande ; 1749-016 ; Lisboa ; Portugal
  
• 关键词：Extreme value theory ; Monte ; Carlo simulation ; Penultimate and ultimate approximations ; System reliability ; Primary 62G32 ; 62N05 ; 62G20 ; Secondary 65C05
• 刊名：Methodology and Computing in Applied Probability
• 出版年：2015
• 出版时间：March 2015
• 年：2015
• 卷：17
• 期：1
• 页码：189-206
• 全文大小：816 KB
• 参考文献：1. Anderson CW (1971) Contributions to the asymptotic theory of extreme values. PhD thesis, University of London
  2. Barlow AA, Proschan F (1975) Statistical theory of reliability and life testing: probability models. Holt, Rinehart and Winston, Inc., USA
  3. Beirlant J, Caeiro F, Gomes MI (2012) An overview and open research topics in statistics of univariate extremes. Revstat 10:1鈥?1
  4. Diebolt J, Guillou A (2005) Asymptotic behaviour of regular estimators. Revstat 3:19鈥?4
  5. Dietrich D, de Haan L, H眉sler J (2002) Testing extreme value conditions. Extremes 5:71鈥?5 CrossRef
  6. Drees H, de Haan L, Li D, Pereira TT (2006) Approximations to the tail empirical distribution function with applications to testing extreme value conditions. J Stat Plan Inference 136:3498鈥?538 CrossRef
  7. Fisher RA, Tippett LHC (1928) Limiting forms of the frequency distributions of the largest or smallest member of a sample. Proc Camb Philos Soc 24:180鈥?90 CrossRef
  8. Gnedenko BV (1943) Sur la distribution limite du terme maximum d鈥檜ne s茅rie al茅atoire. Ann Math 44:423鈥?53 CrossRef
  9. Gnedenko BV, Belyayev YuK, Solovyev AD (1969) Mathematical methods of reliability theory. Academic Press, USA
  10. Gomes MI (1984) Penultimate limiting forms in extreme value theory. Ann Inst Stat Math 36:71鈥?5 CrossRef
  11. Gomes MI (1994) Penultimate behaviour of the extremes. In: Galambos J, et al (eds) Extreme value theory and applications. Kluwer Academic Publishers, pp聽403鈥?18
  12. Gomes MI, de Haan L (1999) Approximations by penultimate extreme value distributions. Extremes 2:71鈥?5 CrossRef
  13. Gomes MI, Pestana DD (1987) Nonstandard domains of attraction and rates of convergence. In: Puri L, et al (eds) New perspectives in theoretical and applied statistics. Wiley, pp 467鈥?77
  14. H眉sler J, Li D (2006) On testing extreme value conditions. Extremes 9:69鈥?6 CrossRef
  15. Jenkinson AF (1955) The frequency distribution of the annual maximum (or minimum) values of meteorological elements. Q J R Meteorol Soc 81:158鈥?71 CrossRef
  16. Kaufmann E (2000) Penultimate approximations in extreme value theory. Extremes 3:39鈥?5 CrossRef
  17. Laio F (2004) Cramer-von Mises and Anderson鈥揇arling goodness of fit tests for extreme value distributions with unknown parameters. Water Resour Res 40:W09308 CrossRef
  18. Raoult JP, Worms R (2003) Rate of convergence for the generalized Pareto approximation of the excesses. Adv Appl Probab 35:1007鈥?027 CrossRef
  19. Reis P, Canto e Castro L (2009) Limit model for the reliability of a regular and homogeneous series-parallel system. Revstat 7:227鈥?43
  20. Samaniego F (1985) On closure of the IFR class under formation of coherent systems. IEEE Trans Reliab 34:69鈥?2 CrossRef
  21. von Mises R (1936) La distribution de la plus grande de / n valeurs. Revue Math. Union Interbalcanique 1:141鈥?60. Reprinted in Selected Papers of Richard von Mises. Amer Math Soc (1964) 2:271鈥?94
  
• 刊物主题：Statistics, general; Life Sciences, general; Electrical Engineering; Economics general; Business/Management Science, general;
• 出版者：Springer US
• ISSN：1573-7713

文摘

In reliability theory any coherent system can be represented as either a series-parallel or a parallel-series system. Its lifetime can thus be written as the minimum of maxima or the maximum of minima. For large-scale coherent systems it is sensible to assume that the number of system components goes to infinity. Then, the possible non-degenerate extreme value laws either for maxima or for minima are eligible candidates for the system reliability or at least for the finding of adequate lower and upper bounds for the reliability. The identification of the possible limit laws for the system reliability of homogeneous series-parallel (or parallel-series) systems has already been done under different frameworks. However, it is well-known that in most situations such non-degenerate limit laws are better approximated by an adequate penultimate distribution. Dealing with regular and homogeneous parallel-series systems, we assess both theoretically and through Monte-Carlo simulations the gain in accuracy when a penultimate approximation is used instead of the ultimate one.