Answers are grounded in this paper and cite their sources.
Investigates point and interval estimation methods in statistical analysis, highlighting importance for accurate modeling.
In this paper, we investigate the power-modified Lindley distribution by addressing two key objectives. First, we derive explicit expressions for the single and product moments of the order statistics. The derived moments are further used to compute the variances and covariances of the order statistics under different parameter configurations. Second, we develop statistical inference procedures through point and interval estimation. Point estimation is carried out using five methods: maximum likelihood estimation, least squares estimation, percentile estimation, Anderson–Darling estimation, and Cramér–von Mises estimation. To construct interval estimates, three bootstrap approaches – standard bootstrap, bias-corrected percentile bootstrap, and a percentile bootstrap – are employed in conjunction with the proposed point estimation methods. An extensive simulation study under various parameter settings is conducted to assess the accuracy of the derived expressions and compare the performance of the estimation procedures. The results confirm the accuracy of the theoretical expressions and show that the maximum likelihood and Cramér–von Mises methods consistently provide the most accurate parameter estimates, while the bootstrap confidence intervals achieve the desired coverage probabilities, particularly for larger sample sizes. Finally, the proposed methods are illustrated using two real-world datasets, where the power-modified Lindley distribution provides a superior fit compared with the competing lifetime models in terms of goodness-of-fit measures.
No takes yet. Share an insight, caveat, or question.
Diyali et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: