Kybernetika 59 no. 2, 209-233, 2023

Theoretical aspects of total time on test transform of weighted variables and applications

Mojtaba Esfahani, Gholam Reza Mohtashami-Borzadaran and Mohammad AminiDOI: 10.14736/kyb-2023-2-0209

Abstract:

Although the total time on test (\textit{TTT}) transform is not a newly discovered concept, it has many applications in various fields. On the other hand, weighted distributions are extensively developed by the statisticians to tackle the insufficiency of the standard statistical distributions in modeling the arising data from real-world problems in the contexts like medicine, ecology, and reliability engineering. This paper develops the \textit{TTT} transform for the weighted random variables and investigates the behavior of the failure rate function of such variables based on the \textit{TTT} transform. In addition, the conditions for establishing the $TTT$ transform ordering for weight variables and its relationship with some stochastic orders have been investigated, and the conditions for establishing the \textit{TTT} transform order as well as the presentation of the new better than used in total time on test transform (\textit{NBUT}) class of the weighted variables have also been studied. Finally, by analyzing the real data sets, applications of the transform introduced in the fit of a model is presented, and it is shown that weighted models have a significant advantage over the base models.

Keywords:

total time on test transform, generalized failure rate, generalized reversed failure rate, new better than used in total time on test transform, weight function

Classification:

62N05, 62E15, 62P99

paper.pdf

References:

  1. A. M. Abd-Elfattah: Goodness of fit test for the generalized Rayleigh distribution with unknown parameters. J. Statist. Comput. Simul. 81 (2011), 3, 357-366.   DOI:10.1080/00949650903348155
  2. B. C. Arnold: Pareto Distributions Fairland. International Cooperative Publishing House. Maryland 1983.   CrossRef
  3. R. E. Barlow: Geometry of the total time on test transform. Naval Res. Logist. Quarterly 26 (1979), 3, 393-402.   DOI:10.1002/nav.3800260303
  4. R. E. Barlow and R. Campo: Total time on test processes and applications to failure data analysis. In: Reliability and Fault Tree Analysis, SIAM, Philadelphia 1975.   CrossRef
  5. J. Bartoszewicz: On a representation of weighted distributions. Statist. Probab. Lett. 79 (2009), 15, 1690-1694.   DOI:10.1016/j.spl.2009.04.007
  6. J. Bartoszewicz and M. Skolimowska: Preservation of classes of life distributions and stochastic orders under weighting. Statist. Probab. Lett. 76 (2006), 6, 587-596.   DOI:10.1016/j.spl.2005.09.003
  7. Z. Behdani, G. R. Mohtashami Borzadaran and B. S. Gildeh: Relationship between the weighted distributions and some inequality measures. Commun. Statist. - Theory Methods 47 (2018), 22, 5573-5589.   DOI:10.1080/03610926.2017.1397171
  8. Z. Behdani, G. R. Mohtashami Borzadaran and B. S. Gildeh: Connection of generalized failure rate and generalized reversed failure rate with inequality curves. Int. J. Reliab. Quality Safety Engrg. 26 (2019), 02, 1950006.   DOI:10.1142/S0218539319500062
  9. M. Benduch-Fraszczak: Some properties of the proportional odds model. Appl. Math. 37 (2010), 2, 247-256.   DOI:10.4064/am37-2-9
  10. B. Bergman and B. Klefsjö: A graphical method applicable to age-replacement problems. IEEE Trans. Reliab. 31 (1982), 5, 478-481.   DOI:10.1109/TR.1982.5221439
  11. B. Bergman and B. Klefsjö: The total time on test concept and its use in reliability theory. Oper. Res. 32 (1984), 3, 596-606.   DOI:10.1287/opre.32.3.596
  12. M. Bieniek: Optimal bounds for the mean of the total time on test for distributions with decreasing generalized failure rate. Statistics 50 (2016), 6, 1206-1220.   DOI:10.1080/02331888.2016.1148152
  13. M. Bieniek and M. Szpak: Sharp bounds for the mean of the total time on test for distributions with increasing generalized failure rate. Statistics 52 (2018), 4, 818-828.   DOI:10.1080/02331888.2017.1410153
  14. D. R. Cox: Renewal Theory. Metrheun's Monograph. Barnes and Noble. Inc., New York 1962.   CrossRef
  15. M. Esfahani, M. Amini and G. R. Mohtashami Borzadaran: On the applications of total time on test transform in reliability. J. Statist. Sci. 15 (2021), 1, 1-23.   DOI:10.52547/jss.15.1.1
  16. E. Fagiuoli, F. Pellerey and M. Shaked: A characterization of the dilation order and its applications. Statist. Papers 40 (1999), 4, 393-406.   DOI:10.1007/BF02934633
  17. A. M. Franco-Pereira, R. E. Lillo and M. Shaked: The decreasing percentile residual life ageing notion. Statistics 46 (2012), 5, 587-603.   DOI:10.1080/02331888.2010.543467
  18. A. M. Franco-Pereira and M. Shaked: The total time on test transform and the decreasing percentile residual life aging notion Statist. Methodology 18 (2014), 32-40.   DOI:10.1016/j.stamet.2013.09.003
  19. R. A. Fisher: The effect of methods of ascertainment upon the estimation of frequencies. Ann. Eugenics 6 (1934), 1), 13-25.   DOI:10.1111/j.1469-1809.1934.tb02105.x
  20. M. L. Gamiz, R. Nozal-Canadas and R. Raya-Miranda: TTT-SiZer: A graphic tool for aging trends recognition. Reliab. Engrg. System Safety 202 (2020), 107010.   DOI:10.1016/j.ress.2020.107010
  21. A. L. Haines and N. D. Singpurwalla: Some contributions to the stochastic characterization of wear. Reliability and Biometry, Statistical Analysis of Lifelength (F. Proschan and R. J. Serfling, eds.), SIAM, Philadelphia 1974, pp. 47-80.   CrossRef
  22. S. Izadkhah, A. H. Rezaei, M. Amini and G. R. Mohtashami Borzadaran: A general approach for preservation of some aging classes under weighting. Commun. Statistics-Theory Methods 42 (2013), 10, 1899-1909.   DOI:10.1080/03610926.2011.598998
  23. S. Izadkhah, M. Amini and G. R. Mohtashami Borzadaran: On preservation under univariate weighted distributions. Appl. Math. 60 (2015), 4, 453-467.   DOI:10.1007/s10492-015-0105-7
  24. I. Jewitt: Choosing between risky prospects: the characterization of comparative statics results, and location independent risk. Management Sci. 35 (1989), 1, 60-70.   DOI:10.1287/mnsc.35.1.60
  25. B. Klefsjo: On aging properties and total time on test transforms. Scandinav. J. Statist, (1982), 37-41.   DOI:10.2307/20555042
  26. B. Klefsjo: TTT-transforms - A useful tool when analysing different reliability problems. Reliab. Engrg. 15 (1986), 3, 231-241.   DOI:10.1016/0143-8174(86)90012-0
  27. B. Klefsjo: TTT-plotting - A tool for both theoretical and practical problems. J. Statist. Planning Inference 29 (1991), 1-2, 99-110.   DOI:10.1016/0378-3758(92)90125-C
  28. B. Klefsjo and U. Westberg: TTT plotting and maintenance policies. Quality Engrg. 9 (1996), 2, 229-235.   DOI:10.1080/08982119608919039
  29. S. C. Kochar, X. Li and M. Shaked: The total time on test transform and the excess wealth stochastic orders of distributions. Adv. Appl. Probab. 34 (2002), 4, 826-845.   DOI:10.1017/S0001867800011939
  30. D. Kumar and U. Westberg: Maintenance scheduling under age replacement policy using proportional hazards model and ttt-plotting. Europ. J. Oper. Res. 99 (1997), 3, 507-515.   DOI:10.1016/S0377-2217(96)00317-7
  31. C. D. Lai and M. Xie: Stochastic Ageing and Dependence for Reliability. Springer Science and Business Media, 2006.   CrossRef
  32. A. W. Marshall and I. Olkin: A new method for adding a parameter to a family of distributions with application to the exponential and Weibull families. Biometrika 84 (1997), 3, 641-652.   DOI:10.1093/biomet/84.3.641
  33. N. Misra, N. Gupta and I. D. Dhariyal: Preservation of some aging properties and stochastic orders by weighted distributions. Commun. Statist. - Theory Methods 37 (2008), 5, 627-644.   DOI:10.1080/03610920701499506
  34. N. U. Nair and P. G. Sankaran: Some new applications of the total time on test transforms. Statist. Methodology 10 (2013), 1, 93-102.   DOI:10.1016/j.stamet.2012.07.003
  35. N. U. Nair, P. G. Sankaran and B. V. Kumar: Total time on test transforms of order n and their implications in reliability analysis. J. Appl. Probab. 45 (2008), 4, 1126-1139.   DOI:10.1017/S0021900200005027
  36. T. Nguyen and T. Nguyen: A linear time partitioning algorithm for frequency weighted impurity functions. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE 2020, pp. 5375-5379.   DOI:10.1109/icassp40776.2020.9054763
  37. M. D. Nichols and W. J. Padgett: A bootstrap control chart for Weibull percentiles. Quality Reliab. Engrg. Int. 22 (2006), 2, 141-151.   DOI:10.1002/qre.691
  38. W. J. Padgett and J. D. Spurrier: Shewhart-type charts for percentiles of strength distributions. J. Quality Technol. 22 (1990), 283-288.   DOI:10.1080/00224065.1990.11979260
  39. G. P. Patil: Weighted Distributions. Wiley StatsRef: Statistics Reference Online, 2014.   CrossRef
  40. G. P. Patil and J. K. Ord: On size-biased sampling and related form-invariant weighted distributions. Sankhya 38B (1976), 48-61.   DOI:10.2307/20634829
  41. T. G. Pham and N. Turkkan: The Lorenz and the scaled total-time-on-test transform curves: a unified approach. IEEE Trans. Reliab. 43 (1994), 1, 76-84.   DOI:10.1109/24.285115
  42. C. R. Rao: On discrete distributions arising out of methods of ascertainment. Sankhya: Indian J. Statist. Ser. A, (1965), 311-324.   CrossRef
  43. K. R. Rao and P. V. N. Prasad: Graphical methods for reliability of repairable equipment and maintenance planning. In: Proc. Annual Reliability and Maintainability Symposium, International Symposium on Product Quality and Integrity (Cat. No. 01CH37179), IEEE 2001, pp. 123-128.   CrossRef
  44. A. Saghir, G. G. Hamedani, S. Tazeem and A. Khadim: Weighted distributions: A brief review, perspective and characterizations. Int. J. Statist. Probab. 7 (2017), 1, 109-131.   DOI:10.5539/ijsp.v6n3p109
  45. M. Shaked and J. G. Shanthikumar: Stochastic Orders. Springer Science and Business Media, 2007.   CrossRef
  46. R. L. Smith and J. C. Naylor: A comparison of maximum likelihood and Bayesian estimators for the three-parameter Weibull distribution. Appl. Statist. 36 (1987), 358-369.   DOI:10.2307/584482
  47. M. A. Spiroiu: Estimation of total time on test for large samples. In: MATEC Web of Conferences, EDP Sciences 2017, Vol. 112, p. 09008).   DOI:10.1051/matecconf/201711209008
  48. F. B. Sun and D. B. Kececloglu: A new method for obtaining the TTT plot for a censored sample. In Annual Reliability and Maintainability. In: Proc. Symposium. (Cat. No. 99CH36283), IEEE 1999, pp. 112-117.   DOI:10.1109/rams.1999.744105