Statistical Inference for the Lindley-Exponential Distribution Using Lower Record Values

Norouzi Firooz, Mehrdad; Jabbari Khamnei, Hossein; Heydari, Ali Akbar

doi:10.22124/cse.2025.31858.1127

Document Type : Original Article

Authors

Department of Statistics, Faculty of Mathematics, Statistics, and Computer Science, University of Tabriz, Tabriz, Iran

https://doi.org/10.22124/cse.2025.31858.1127

Abstract

This paper presents a comprehensive study on statistical inference for the Lindley-Exponential (LE) distribution based on lower record values. We derive key distributional properties of the LE model, including the density and moments of lower record statistics. Both classical and Bayesian frameworks are developed for parameter estimation. The maximum likelihood method is employed to obtain point estimates and asymptotic confidence intervals. For the Bayesian approach, independent gamma priors are assumed for the parameters, and estimation is conducted under symmetric (squared error) and asymmetric (LINEX) loss functions. Since the posterior distributions are analytically intractable, we use the Tierney–Kadane approximation and a Metropolis–Hastings algorithm within the Gibbs framework. Furthermore, we address the problem of predicting future lower record values using both maximum likelihood and Bayesian predictive distributions. Extensive Monte Carlo simulations are conducted to evaluate the performance of the proposed estimators and predictors. The results indicate that the Bayesian estimators under squared error loss often yield lower expected risks, and the predictive accuracy improves with the number of observed records. The methodologies developed in this study are particularly useful for modeling and predicting extreme or record-breaking events in fields such as reliability engineering, meteorology, and economics.

Keywords

References

[1] Cakmakyapan, S., & Ozel, G. (2016). The Lindley family of distributions: Properties and applications. Hacettepe Journal of Mathematics and Statistics, 46(6), 1113–1137.

[2] Chandler, K. (1952). The distribution and frequency of record values. Journal of the Royal Statistical Society: Series B (Methodological), 14(2), 220–228.

[3] Resnick, S. I. (1973). Record values and maxima. The Annals of Probability, 650–662.

[4] Shorrock, R. W. (1973). Record values and inter-record times. Journal of Applied Probability, 10(3), 543–555.

[5] Glick, N. (1978). Breaking records and breaking boards. The American Mathematical Monthly, 85(1), 2–26.

[6] Nevzorov, V. B. (1988). Records. Theory of Probability & Its Applications, 32(2), 201–228.

[7] Ahsanullah, M., & Nevzorov, V. B. (2025). Record statistics. In International Encyclopedia of Statistical Science (pp. 2132–2141). Springer.

[8] Balakrishnan, N., & Ahsanullah, M. (1994). Relations for single and product moments of record values from Lomax distribution. Sankhyā: The Indian Journal of Statistics, Series B, 140–146.

[9] Arnold, B. C., Balakrishnan, N., & Nagaraja, H. N. (2011). Records. John Wiley & Sons.

[10] Dey, S., & Dey, T. (2012). Bayesian estimation of the parameter and reliability of a Rayleigh distribution using records. Model Assisted Statistics and Applications, 7(2), 81–90.

[11] Dey, S., Dey, T., Salehi, M., & Ahmadi, J. (2013). Bayesian inference of generalized exponential distribution based on lower record values. American Journal of Mathematical and Management Sciences, 32(1), 1–18.

[12] Kızılaslan, F., & Nadar, M. (2014). Estimations for proportional reversed hazard rate model distributions based on upper record values and inter-record times. İstatistik: Journal of the Turkish Statistical Association, 7(2), 55–62.

[13] Kızılaslan, F., & Nadar, M. (2015). Estimation with the generalized exponential distribution based on record values and inter-record times. Journal of Statistical Computation and Simulation, 85(5), 978–999.

[14] Kızılaslan, F., & Nadar, M. (2016). Estimation and prediction of the Kumaraswamy distribution based on record values and inter-record times. Journal of Statistical Computation and Simulation, 86(12), 2471–2493.

[15] Tarvirdizade, B., & Ahmadpour, M. (2016). Estimation of the stress–strength reliability for the two-parameter bathtub-shaped lifetime distribution based on upper record values. Statistical Methodology, 31, 58–72.

[16] Ahmadi, J., & Doostparast, M. (2006). Bayesian estimation and prediction for some life distributions based on record values. Statistical Papers, 47(3), 373–392.

[17] Doostparast, M., & Balakrishnan, N. (2013). Pareto analysis based on records. Statistics, 47(5), 1075–1089.

[18] Zanjiran, F., & MirMostafaee, S. M. T. K. (2024). On estimation and prediction for the XLindley distribution based on record data. Reliability: Theory & Applications, 19(2), 258–272.

[19] Pak, A., & Dey, S. (2019). Statistical inference for the power Lindley model based on record values and inter-record times. Journal of Computational and Applied Mathematics, 347, 156–172.

[20] Dey, S., Dey, T., & Luckett, D. J. (2016). Statistical inference for the generalized inverted exponential distribution based on upper record values. Mathematics and Computers in Simulation, 120, 64–78.

[21] Amiri, Z. K., & MirMostafaee, S. (2023). Analysis for the xgamma distribution based on record values and inter-record times with application to prediction of rainfall and COVID-19 records. Statistics in Transition, 24(5), 89–108.

[22] Khoshkhoo Amiri, Z., & MirMostafaee, S. (2024). Statistical inference for a two-parameter distribution with a bathtub-shaped or increasing hazard rate function based on record values and inter-record times with an application to COVID-19 data. Journal of Statistical Computation and Simulation, 94(9), 1965–1996.

[23] Bastan, F., & MirMostafaee, S. (2022). Estimation and prediction for the Poisson-exponential distribution based on records and inter-record times: A comparative study (pp. 381–405).

[24] Varian, H. R. (1975). A Bayesian approach to real estate assessment. In Studies in Bayesian Econometrics and Statistics in Honor of Leonard J. Savage.

[25] Tierney, L., & Kadane, J. B. (1986). Accurate approximations for posterior moments and marginal densities. Journal of the American Statistical Association, 81(393), 82–86.

[26] Basak, P., & Balakrishnan, N. (2003). Maximum likelihood prediction of future record statistic. In Mathematical and Statistical Methods in Reliability (pp. 159–175). World Scientific.

Computational Sciences and Engineering

Statistical Inference for the Lindley-Exponential Distribution Using Lower Record Values

References

References

Volume 5, Issue 1
April 2025
Pages 151-186

Statistical Inference for the Lindley-Exponential Distribution Using Lower Record Values

References

References

Volume 5, Issue 1April 2025Pages 151-186

Volume 5, Issue 1
April 2025
Pages 151-186