Skip to main content
Log in

Analysis of an Inverted Modified Lindley Distribution Using Dual Generalized Order Statistics

  • Published:
Strength of Materials Aims and scope

In this paper, the estimation of the unknown parameters of the inverted modified Lindley distribution using the concept of dual generalized order statistics is investigated from both classical and Bayesian viewpoints. Based on this considered distribution, first, the maximum likelihood estimator and approximate confidence interval of the model parameter are obtained using order statistics and lower record values. Next, we consider Bayes estimation under the symmetric loss function using a gamma prior. We also derived the highest posterior density credible interval based on the Metropolis–Hastings algorithm. Moreover, the results for single and product moments based on dual generalized order statistics using this distribution are derived. Based on order statistics and lower record values, Monte Carlo simulations are carried out to examine the enforcement of the proposed estimators, and a dataset is investigated for both order statistics and lower record values for illustrative purposes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.

Similar content being viewed by others

References

  1. C. Chesneau, L. Tomy, J. Gillariose, and F. Jamal, “The inverted modified Lindley distribution,” J. Stat. Theory & Pract., 14, No. 3 (2020), 10.1007/s42519-020-00116-5.

  2. U. Kamps, A Concept of Generalized Order Statistics, B.G. Teubner Stuttgart (1995).

    Book  Google Scholar 

  3. P. Pawlas, and D. Szynal, “Recurrence relations for single and product moments of lower generalized order from the inverse Weibull distribution,” Demonstratio Mathematica, 34, No. 2, 353-358 (2001).

    Article  Google Scholar 

  4. M. Burkschat, E. Cramer, and U. Kamps, “Dual generalized order statistic,”. Metron LXI, 13-26 (2003).

  5. R. U. Khan and D. Kumar, “On moments of generalized order statistics fromex-ponentiated Pareto distribution and its characterization,” Appl. Math. Sci. (Ruse), 4, 2711-2722 (2010).

    Google Scholar 

  6. R. U. Khan and M. A. Khan, “Dual generalized order statistics from family of J-shaped distribution and its characterization,” J. King Saud Univ.Sci., 27, 285-291(2015).

    Article  Google Scholar 

  7. M. J. S. Khan and S. Iqrar, “On moments of dual generalized order statistics from Topp-Leone distribution,”Communication in Statistics-Theory and Methods, 48, No. 3, 479- 492 (2019).

    Article  Google Scholar 

  8. R. U. Khan, Z. Anwar, and H. Athar, “Recurrence relations for single and product moments of dual generalized order from exponentiated Weibull distribution,” Aligarh. J. Statist., 28, 37-45 (2008).

    Google Scholar 

  9. R. U. Khan and D. Kumar, “Expectation Identities of lower generalized order statistics from generalized exponential distribution and its characterization,” Mathematical Methods of Statistics, 20, 150-157 (2011).

    Article  Google Scholar 

  10. D. Kumar and S. Dey, “Relations for moments of generalized order statistics from extended exponential distribution,” Am. J. Math. & Manag. Sci., 36, No. 4, 378-400 (2017).

    Google Scholar 

  11. D. Kumar, “On moments of lower generalized order statistics from exponentiated Lomax distribution, Am. J. Math. & Manag. Sci., 32, No. 4, 238-256 (2013).

  12. D. Kumar, “Relations for marginal and joint moment generating functions of Marshall–Olkin extended Logistic distribution based on lower generalized order statistics and characterization,” Am. J. Math. & Manag. Sci., 32, No. 1, 19-39 (2013).

  13. D. Kumar, “Lower generalized order statistics based on inverse Burr distribution,” Am. J. Math. & Manag. Sci., 35, No. 1, 15-35 (2016).

    Google Scholar 

  14. A. Gelman, J. B. Carlin, H. S. Stern, et al., Bayesian Data Analysis, 2nd Ed. Chapman and Hall/CRC, USA (2004).

    Google Scholar 

  15. S. M. Lynch, Introduction to Applied Bayesian Statistics and Estimation for Social Scientists, Springer, New York (2007).

    Book  Google Scholar 

  16. M.-H. Chen and Q.-M. Shao, “Monte Carlo estimation of Bayesian credible and HRD intervals,” J. Comput. Graph. Stat., 8, No. 1, 69-92 (1999).

    Google Scholar 

  17. J. M. Pavia, “Testing goodness-of-fit with the kernel density estimator: GoFKernel,” J. Stat. Soft., 66, No. 1, 1-27 (2015).

    Google Scholar 

  18. D. Kundu, “Bayesian inference and life testing plan for the Weibull distribution in presence of progressive censoring,” Technometrics, 50, No. 2, 144-154 (2008).

    Article  Google Scholar 

  19. M. Plummer, N. Best, K. Cowles, and K. Vines, “CODA: convergence diagnosis and output analysis for MCMC,” R. News, 6, No. 1, 7-11 (2006).

    Google Scholar 

  20. A. Henningsen, and O. Toomet, “maxLik: A package for maximum likelihood estimation in R,” Comput. Stat., 26, No. 3, 443–458 (2011).

    Article  Google Scholar 

  21. Z. Keller, A. R. R. Kamath, and U. D. Perera, “Reliability analysis of CNC machine tools,” Reliability Eng., 3, No. 6, 449-473 (1982).

    Article  Google Scholar 

  22. V. N. Treyer, “A distribution law of random variables for the reliability computations for wearable parts of machines and devices,” Doklady Acad. Nauk, Belorus, USSR (in Russian), 8, 47-50 (1964).

  23. V. K. Sharma, S. K. Singh, U. Singh, and V. Agiwal, “The inverse Lindley distribution: a stress–strength reliability model with application to head and neck cancer data,” J. Indust. & Product. Eng., 32, No. 3, 162-173 (2015).

    Article  Google Scholar 

  24. L. Guo and W. Gui, “Bayesian and classical estimation of the inverse Pareto distribution and its application to strength–stress models,” Am. J. Math. & Manag. Sci., 37, No. 1, 80-92 (2018).

    Google Scholar 

  25. P. R. D. Marinho, R. B. Silva, M. Bourguignon, et al., “Adequacy Model: An R package for probability distributions and general purpose optimization,” PloS One, 14, No. 8, 10.1371/journal.pone.0221487 (2019).

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to D. Kumar.

Additional information

Translated from Problemy Mitsnosti, No. 5, p. 124, September – October, 2022.

APPENDIX

APPENDIX

Lemma 1. For (a1, a2, and a3) > 0, let

$$ {\Delta }_1\left({a}_1,{a}_2,{a}_3\right)={\int}_0^{\infty }{y}^{\alpha_1-2}\left(\left(1+{a}_3\right){e}^{\frac{a_3}{y}}+\frac{2{a}_3}{y}-1\right)\exp \left(-\frac{a_2{a}_3}{y}\right) dy. $$
(16)

Then

$$ {\Delta }_1\left({a}_1,{a}_2,{a}_3\right)=\left(\frac{\left(1+{a}_3\right)\Gamma \left(1-{a}_1\right)}{{\left({a}_3\left({a}_2-1\right)\right)}^{1-{a}_1}}+\frac{2{a}_3\Gamma \left(2-{a}_1\right)}{{\left({a}_2{a}_3\right)}^{2-{a}_1}}-\frac{\Gamma \left(1-{a}_1\right)}{{\left({a}_2{a}_3\right)}^{1-{a}_1}}\right). $$

Proof. We can write Eq. (16) as

$$ {\displaystyle \begin{array}{c}{\Delta }_1\left({a}_1,{a}_2,{a}_3\right)=\left(1+{a}_3\right){\int}_0^{\infty }{y}^{\alpha_1-2}\exp \left(-\frac{\left({a}_2-1\right){a}_3}{y}\right) dy+2{a}_3{\int}_0^{\infty }{y}^{\alpha_1-3}\exp \left(-\frac{a_2{a}_3}{y}\right) dy\kern0.5em \\ {}-{\int}_0^{\infty }{y}^{\alpha_1-2}\exp \left(-\frac{a_2{a}_3}{y}\right) dy\kern0.5em \\ {}\begin{array}{c}=\frac{\left(1+{a}_3\right)}{{\left({a}_3\left({a}_2-1\right)\right)}^{1-{a}_1}}{\int}_0^{\infty }{u}^{-{a}_1}{e}^{-u} du+\frac{2{a}_3}{{\left({a}_2{a}_3\right)}^{2-{a}_1}}{\int}_0^{\infty }{v}^{1-{a}_1}{e}^{-v} dv\\ {}-\frac{1}{{\left({a}_2{a}_3\right)}^{1-{a}_1}}{\int}_0^{\infty }{v}^{-{a}_1}{e}^{-v} dv,\end{array}\end{array}} $$

where \( u=\frac{a_3\left({a}_2-1\right)}{y} \) and\( v=\frac{a_2{a}_3}{y}. \)

Lemma 2. For positive real numbers a1, a2, a3, a4 and a5,, let

$$ {\displaystyle \begin{array}{c}{\Delta }_2\left({a}_1,{a}_2,{a}_3,{a}_4,{a}_5\right)={\int}_0^{\infty }{\int}_y^{\infty }{y}^{\alpha_1-2}{z}^{\alpha_3-2}{e}^{-\frac{a_5{a}_2}{y}}\left(\left(1+{a}_5\right){e}^{\frac{a_5}{y}}+\frac{2{a}_5}{y}-1\right)\\ {}\times {e}^{-\frac{a_5{a}_4}{z}}\left(\left(1+{a}_5\right){e}^{\frac{a_5}{z}}+\frac{2{a}_5}{z}-1\right) dzdy.\end{array}} $$
(17)

Then,

$$ {\displaystyle \begin{array}{c}{\Delta }_2\left({a}_1,{a}_2,{a}_3,{a}_4,{a}_5\right)=\frac{{\left(1+{a}_5\right)}^2\Gamma \left(2-{a}_1-{a}_3\right)}{{\left(\left({a}_4-1\right){a}_5\right)}^{2-{a}_1-{a}_3}\left(1-{a}_3\right){\left(1+\frac{a_2-1}{a_4-1}\right)}^{2-{a}_1-{a}_3}}\\ {}\times 2{F}_1\left(1,2-{a}_1-{a}_3;2-{a}_3;\frac{1}{1+\frac{a_2-1}{a_4-1}}\right)\\ {}\begin{array}{c}+\frac{2{a}_5\left(1+{a}_5\right)\Gamma \left(2-{a}_1-{a}_3\right)}{\left(1-{a}_3\right){\left({a}_5\left({a}_4-1\right)\right)}^{3-{a}_1-{a}_3}{\left(1+\frac{a_2}{a_4-1}\right)}^{3-{a}_1-{a}_3}}2{F}_1\left(1,3-{a}_1-{a}_3;2-{a}_3;\frac{1}{1+\frac{a_2}{a_4-1}}\right)\\ {}-\frac{\left(1+{a}_5\right)\Gamma \left(2-{a}_1-{a}_3\right)}{\left(1-{a}_3\right){\left({a}_5\left({a}_4-1\right)\right)}^{2-{a}_1-{a}_3}{\left(1+\frac{a_2}{a_4-1}\right)}^{2-{a}_1-{a}_3}}2{F}_1\left(1,2-{a}_1-{a}_3;2-{a}_3;\frac{1}{1+\frac{a_2}{a_4-1}}\right)\\ {}\begin{array}{c}+\frac{2{a}_5\left(1+{a}_5\right)\Gamma \left(2-{a}_1-{a}_3\right)}{\left(2-{a}_3\right){\left({a}_5{a}_4\right)}^{3-{a}_1-{a}_3}{\left(1+\frac{a_2-1}{a_4}\right)}^{3-{a}_1-{a}_3}}2{F}_1\left(1,3-{a}_1-{a}_3;3-{a}_3;\frac{1}{1+\frac{a_2-1}{a_4}}\right)\\ {}+\frac{{\left(2{a}_5\right)}^2\Gamma \left(4-{a}_1-{a}_3\right)}{\left(2-{a}_3\right){\left({a}_5{a}_4\right)}^{3-{a}_1-{a}_3}{\left(1+\frac{a_2}{a_4}\right)}^{4-{a}_1-{a}_3}}2{F}_1\left(1,4-{a}_1-{a}_3;3-{a}_3;\frac{1}{1+\frac{a_2}{a_4}}\right)\\ {}\begin{array}{c}+\frac{2{a}_5\Gamma \left(3-{a}_1-{a}_3\right)}{\left(2-{a}_3\right){\left({a}_5{a}_4\right)}^{3-{a}_1-{a}_3}{\left(1+\frac{a_2}{a_4}\right)}^{3-{a}_1-{a}_3}}2{F}_1\left(1,3-{a}_1-{a}_3;3-{a}_3;\frac{1}{1+\frac{a_2}{a_4}}\right)\\ {}-\frac{\left(1+{a}_5\right)\Gamma \left(2-{a}_1-{a}_3\right)}{\left(1-{a}_3\right){\left({a}_5{a}_4\right)}^{2-{a}_1-{a}_3}{\left(1+\frac{a_2-1}{a_4}\right)}^{2-{a}_1-{a}_3}}2{F}_1\left(1,2-{a}_1-{a}_3;2-{a}_3;\frac{1}{1+\frac{a_2-1}{a_4}}\right)\\ {}\begin{array}{c}-\frac{2{a}_5\Gamma \left(3-{a}_1-{a}_3\right)}{\left(1-{a}_3\right){\left({a}_5{a}_4\right)}^{3-{a}_1-{a}_3}{\left(1+\frac{a_2}{a_4}\right)}^{2-{a}_1-{a}_3}}2{F}_1\left(1,3-{a}_1-{a}_3;2-{a}_3;\frac{1}{1+\frac{a_2}{a_4}}\right)\\ {}+\frac{\Gamma \left(2-{a}_1-{a}_3\right)}{\left(1-{a}_3\right){\left({a}_5{a}_4\right)}^{2-{a}_1-{a}_3}{\left(1+\frac{a_2}{a_4}\right)}^{2-{a}_1-{a}_3}}2{F}_1\left(1,2-{a}_1-{a}_3;2-{a}_3;\frac{1}{1+\frac{a_2}{a_4}}\right),\end{array}\end{array}\end{array}\end{array}\end{array}} $$

where

$$ 2{F}_1\left({b}_1,{b}_2,{b}_3;y\right)=\sum_{k=0}^{\infty}\frac{{\left({b}_1\right)}_k{\left({b}_2\right)}_k{y}^k}{{\left({b}_3\right)}_kk!}. $$
(18)

Proof. We have

$$ {\displaystyle \begin{array}{c}{\Delta }_2\left({p}_1,{p}_2,{q}_1,{q}_2\right)={\int}_0^1{y}^{p_1}{\left(2-{y}^{\alpha}\right)}^{p_2}\left({\int}_0^y{z}^{q_1}\left(2-{z}^{\alpha}\right) dz\right) dy\\ {}=\frac{2^{\frac{q_1+1}{\alpha }+{q}_2}}{\alpha }{\int}_0^1{y}^{p_1}{\left(2-{y}^{\alpha}\right)}^{p_2}\left({\int}_0^{\frac{y}{2}}{t}^{\frac{q_1+1}{\alpha }-1}{\left(1-t\right)}^{q_2} dt\right) dy\\ {}=\frac{2^{\frac{q_1+1}{\alpha }+{q}_2}}{\alpha }{\int}_0^1{y}^{p_1}{\left(2-{y}^{\alpha}\right)}^{p_2} Bet\left(\frac{q_1+1}{\alpha },{q}_2+1,\frac{y}{2}\right) dy,\end{array}} $$
(19)

where zα = 2t. Next, we use the following formula

$$ Bet\left(a,b,y\right)={\int}_0^y{t}^{a-1}{\left(1-t\right)}^{b-1} dt={a}^{-1}{y}^a2{F}_1\left(a,1-b,a+1:y\right). $$

Now by using Eq. (19), we obtain

$$ {\Delta }_2\left({p}_1,{p}_2,{q}_1,{q}_2\right)=\frac{2^{q_2}}{q_1+1}{\int}_0^1{y}^{p_1+\frac{q_1+1}{\alpha }}{\left(1-{y}^{\alpha}\right)}^{p_2}2{F}_1\left(\frac{q_1+1}{\alpha },-{q}_2;\frac{q_1+1}{\alpha }+1,\frac{y}{2}\right) dy. $$

In view of Eq. (18), ∆2(p1, p2, q1, q2) can be rewritten as

$$ {\displaystyle \begin{array}{c}{\Delta }_2\left({p}_1,{p}_2,{q}_1,{q}_2\right)=\frac{2^{q_2}}{q_1+1}\sum_{i=0}^{\infty}\frac{{\left(\frac{q_1+1}{\alpha}\right)}_i{\left(-{q}_2\right)}_i}{{\left(\frac{q_1+1}{\alpha}\right)}_ii!}{2}^{-i}{\int}_0^1{y}^{p_1+\frac{q_1+1}{\alpha }+i}{\left(1-{y}^{\alpha}\right)}^{p_2} dy\\ {}=\sum_{i=0}^{\infty}\frac{{\left(\frac{q_1+1}{\alpha}\right)}_i{\left(-{q}_2\right)}_i}{{\left(\frac{q_1+1}{\alpha}\right)}_ii!}{2}^{-i}\frac{1}{\alpha }{2}^{p_2+{q}_2+\frac{\frac{q_1+1}{\alpha }+{p}_1+i+1}{\alpha }}\\ {}\begin{array}{c}\times {\int}_0^{\frac{1}{2}}{v}^{\frac{\frac{q_1+1}{\alpha }+{p}_1+i+1}{\alpha }-1}{\left(1-v\right)}^{p_2} dv\\ {}=\frac{2^{p_2+{q}_2}}{\left({q}_1+1\right)\left(\frac{q_1+1}{\alpha }+{p}_1+1\right)}\sum_{i=0}^{\infty}\sum_{j=0}^{\infty}\frac{{\left(\frac{q_1+1}{\alpha }+{p}_1+1\right)}_{i+j}{\left(\frac{q_1+1}{\alpha}\right)}_i{\left(-{q}_2\right)}_i{\left(-{p}_2\right)}_j}{{\left(\frac{\frac{q_1+1}{\alpha }+{p}_1+1}{\alpha }+1\right)}_{i+j}{\left(\frac{q_1+1}{\alpha }+1\right)}_i}\\ {}\times \frac{2^{-i}{2}^{-j}}{\left(\frac{q_1+1}{\alpha }+{p}_1+i+1\right)}\frac{1}{i!j!},\end{array}\end{array}} $$

where yα = 2v.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kumar, D., Nassar, M., Dey, S. et al. Analysis of an Inverted Modified Lindley Distribution Using Dual Generalized Order Statistics. Strength Mater 54, 889–904 (2022). https://doi.org/10.1007/s11223-022-00466-4

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11223-022-00466-4

Keywords

Navigation