Cybernetics And Systems Analysis logo
Информация редакции Аннотации статей Авторы Архив
КИБЕРНЕТИКА И СИСТЕМНЫЙ АНАЛИЗ
Международний научно-теоретический журнал
УДК 519.2
М. Фусек, Я. Михалек

СТАТИСТИЧЕСКИЙ ВЫВОД ДЛЯ МНОГОКРАТНО ЦЕНЗУРИРОВАННОЙ СЛЕВА
ВЫБОРКИ ТИПА I ДЛЯ РАСПРЕДЕЛЕНИЯ ВЕЙБУЛЛА

Аннотация. Во многих областях науки часто встречаются задачи с цензурированными слева данными с одной или несколькими границами обнаружения. В данной работе предложена процедура для вычисления оценок максимальной правдоподобности параметров многократного цензурирования слева типа I для распределения Вейбулла с учетом разного числа границ обнаружения. Ожидаемая информационная матрица Фишера определена аналитически и ее вид сравнен с выборочной (наблюдаемой) информационной матрицей Фишера. Моделирование основано, главным образом, на свойствах оценок выборок малых размеров. Примеры проиллюстрированы на реальных данных.

Ключевые слова: многократно цензурированная слева выборка, оценка максимальной правдоподобности, распределение Вейбулла, информационная матрица Фишера, цензурирование типа І.



ПОЛНЫЙ ТЕКСТ

Michal Fusek,
Department of Mathematics, Faculty of Electrical Engineering and Communication, Brno University of Technology, Czech Republic, fusekmi@feec.vutbr.cz

Jaroslav Michálek,
Department of Quantitative Methods, Faculty of Military Leadership, University of Defence, Brno, Czech Republic, michalek@fme.vutbr.cz


СПИСОК ЛИТЕРАТУРЫ

  1. Mitra S., Kundu D. Analysis of left censored data from the generalized exponential distribution. J. Stat. Comput. Simul. 2008. Vol. 78. P. 669–679. DOI: https://doi.org/10.1080/00949650701344158.

  2. Aboueissa A.E.-M.A., Stoline M.R. Maximum likelihood estimators of population parameters from doubly left-censored samples. Environmetrics. 2006. Vol. 17. P. 811–826. DOI: https://doi.org/ 10.1002/env.795.

  3. Aboueissa A.E.-M.A. Maximum likelihood estimators of population parameters from multiply censored samples. Environmetrics. 2009. Vol. 20. P. 312–330. DOI: https://doi.org/10.1002/env.931.

  4. Cohen A.C. Truncated and censored samples. New York: Marcel Dekker, 1991. 328 p.

  5. El-Shaarawi A.H., Naderi A. Statistical inference from multiply censored environmental data. Environ. Monit. Assess. 1991. Vol. 17. P. 339–347. DOI: https://doi.org/10.1007/BF00399313.

  6. Fusek M., Michálek J. Statistical analysis of type I multiply left-censored samples from exponential distribution. J. Stat. Comput. Simul. 2015. Vol. 85. P. 2148–2163. DOI: https://doi.org/10.1080/ 00949655.2014.923886.

  7. Fusek M., Michálek J. Statistical methods for analyzing musk compounds concentration based on doubly left-censored samples. Int. J. Math. Model. Method. Appl. Sci. 2013. Vol. 7. P. 755–763.

  8. Cox D.R., Oakes D. Analysis of survival data. New York: Chapman and Hall/CRC, 1984. 201 p.

  9. Barndorff-Nielsen O.E., Cox D.R. Inference and asymptotics. London: Chapman and Hall/CRC, 1994. 360 p.

  10. Lehmann E.L., Casella G. Theory of point estimation, second ed. New York: Springer-Verlag, 1998. 617 p.

  11. Samosonok O.S. Analysis of empirical estimates obtained for Gibbs distribution parameters by the maximum likelihood method. Cybernetics and Systems Analysis. 2013. Vol. 49, N 2. P. 316–324. DOI: https://doi.org/10.1007/s10559-013-9514-3.

  12. El-Shaarawi A.H., Dolan D.M. Maximum likelihood estimation of water concentrations from censored data. Can. J. Fish. Aquat. Sci. 1989. Vol. 46. P. 1033–1039. DOI: https://doi.org/10.1139/ f89-134.

  13. El-Shaarawi, A.H., Esterby, S.R. Replacement of censored observations by a constant: an evaluation. Water Res. 1992. Vol. 26. P. 835–844. DOI: https://doi.org/10.1016/0043-1354(92)90015-V.

  14. Johnson N.L., Kotz S., Balakrishnan N. Continuous univariate distributions, Vol. 1, 2nd ed. New York: John Wiley and Sons, 1994. 784 p.

  15. Banerjee A., Kundu D. Inference based on type-II hybrid censored data from a Weibull distribution. IEEE Trans. Reliab. 2008. Vol. 57. P. 369–378. DOI: https://doi.org/10.1109/TR.2008.916890

  16. Kundu D. On hybrid censored Weibull distribution. J. Stat. Plan. Inference. 2007. Vol. 137. P. 2127–2142. DOI: https://doi.org/10.1016/j.jspi.2006.06.043.

  17. Kundu D. Bayesian inference and life testing plan for the Weibull distribution in presence of progressive censoring. Technometrics. 2008. Vol. 50. P. 144–154. DOI: https://doi.org/10.1198/ 004017008000000217.

  18. Shoari N., DubБ J.S., Chenouri S. Estimating the mean and standard deviation of environmental data with below detection limit observations: Considering highly skewed data and model misspecification. Chemosphere. 2015. Vol. 138. P. 599–608. DOI: https://doi.org/10.1016/ j.chemosphere.2015.07.009.

  19. Joarder A., Krishna H., Kundu D. Inferences on Weibull parameters with conventional type-I censoring. Comput. Stat. Data Anal. 2011. Vol. 55. P. 1–11. DOI: https://doi.org/10.1016/ j.csda.2010.04.006.

  20. Gupta R.D., Kundu D. Generalized exponential distribution. Aust. N. Z. J. Stat. 1999. Vol. 41. P. 173–188. DOI: https://doi.org/10.1111/1467-842X.00072.

  21. Gupta R.D., Kundu D. Generalized exponential distribution: Existing results and some recent developments. J. Stat. Plan. Inference. 2007. Vol. 137. P. 3537–3547. DOI: https://doi.org/10.1016/ j.jspi.2007.03.030.

  22. Zheng G. On the Fisher information matrix in type II censored data from the exponentiated exponential family. Biom. J. 2002. Vol. 44, Iss. 3. P. 353–357. DOI: https://doi.org/10.1002/ 1521-4036(200204)44:3<353::AID-BIMJ353>3.0.CO;2-7.

  23. Gupta R.D., Kundu D. On the comparison of Fisher information of the Weibull and GE distributions. J. Stat. Plan. Inference. 2006. Vol. 136. DOI: P. 3130–3144. https://doi.org/10.1016/j.jspi. 2004.11.013.

  24. Dube S., Pradhan B., Kundu D. Parameter estimation of the hybrid censored log-normal distribution. J. Stat. Comput. Simul. 2011. Vol. 81. DOI: P. 275–287. https://doi.org/10.1080/ 00949650903292650.

  25. Chen D., Lu J.C., Li C.S., Park J. Parameter estimation for bivariate shock models with singular distribution for censored data with concomitant order statistics. Aust. N. Z. J. Stat. 2000. Vol. 42. P. 323–336. DOI: https://doi.org/10.1111/1467-842X.00129.

  26. Helsel D.R. Fabricating data: How substituting values for nondetects can ruin results, and what can be done about it. Chemosphere. 2006. Vol. 65. P. 2434–2439. DOI: https://doi.org/10.1016/ j.chemosphere.2006.04.051.

  27. Helsel D.R. Statistics for censored environmental data using Minitab® and R. New York: John Wiley and Sons, 2012. 344 p.

  28. Fusek M., Michálek J., Vávrová M. Evaluation of contamination data with non-detects using censored distributions. Fresenius Environ. Bull. 2015. Vol. 24. P. 4165–4172.

  29. Voronin A.N. A compromise method in constrained optimization problems. Cybernetics and Systems Analysis. 2013. Vol. 49, N 1. P. 77–80. DOI: https://doi.org/10.1007/s10559-013-9487-2.

  30. Lagarias J.C., Reeds J.A., Wright, M.H., Wright, P.E. Convergence properties of the Nelder–Mead simplex method in low dimensions. SIAM J. Optim. 1998. Vol. 9. P. 112–147. DOI: https://doi.org/ 10.1137/S1052623496303470.

  31. Fahrmeier L., Tutz G. Multivariate statistical modelling based on generalized linear models, second ed. New York: Springer-Verlag, 2001. 518 p.

  32. Efron B., Johnstone I.M. Fisher’s information in terms of the hazard rate. Ann. Stat. 1990. Vol. 18. P. 38–62. DOI: https://doi.org/10.1214/aos/1176347492.

  33. Fusek M., Michálek J. On the confidence intervals for mean of left-censored Weibull distribution. 22nd International Conference on Soft Computing MENDEL 2016, Brno, Czech Republic. 2016. P. 249–254.

  34. Hogg R.V., McKean, J.W., Craig, A. Introduction to Mathematical Statistics, sixth ed. Upper Saddle River (NJ): Pearson Education, 2005. 694 p.

  35. Fichtengoltz G.M. Course on the differential and integral calculus, Vol. 2 [in Russian]. Moscow: Fiz.-Math.-Giz., 1959.
© 2019 Kibernetika.org. All rights reserved.