V. Swapna

V. Swapna

Auto-generated profile, based on publicly available information

V. Swapna

Department of Statistics and Data Science, Christ University, Karnataka, India

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 July 2025
Verified
Book Chapter
Closed access
VSV. Swapna
V. Swapna
EAE. J. Anjana
E. J. Anjana
JSJeevanand E S
Jeevanand E S
Reliability analysis is critical in measuring the effectiveness and detecting the weakness or mode of failure of other systems in various sectors such as engineering, healthcare, and social science. Stress-strength reliability is the measure of the reliability of a component; that is, the likelihood of a given strength being more significant than the applied stress so that the component will perform the intended function satisfactorily. In the present paper, we are concerned with the estimation of stress-strength reliability R=P[Y<X<Z] where X, Y, and Z are independent random variables, with X being the strength of the component and Y, Z being the stress variables. We consider that the underlying random variables have the LMP, which includes exponential and geometric distributions used in reliability analysis because of constant hazard rates. However, progressive Type-II censoring, which is common in life data studies, makes an estimation of R=P[Y<X<Z] cumbersome because data are observed on a progressive basis as units are progressively removed from a study after failure. To overcome these challenges, we have introduced the methods of shrinkage estimation and maximum penalized likelihood estimation (MPLE). The latter adds a penalty term into the likelihood function, improving the estimates, especially if there is missing or censored data. To compare the performance of the proposed estimators, we perform an extensive simulation study and compute Average Estimate (AE), Mean Square Error (MSE), Relative Absolute Bias (RAB), as well as Relative Efficiency (RE). These results come as evidence that shows the usefulness of these methods in cases with specific needs for accurate quantification of uncertainty and prediction. The results benefit particular application domains, namely cryptography, random number generators or defense methods. This work extends previous investigations in stress-strength reliability assessment, which have been conducted, among others, by Tong (1974, 1975), Johnson (1975), Bai and Hong (1992), Jeevanand and Nair (1994), Krishnamoorthy et al. (2007). Thus, this paper is built around an original line of thought by presenting the shrinkage and penalized estimations for R=P[Y<X<Z] within increasingly Type-II censoring. This research is valuable for enhancing system reliability estimation based on stochastically incomplete data and censoring.

3 February 2026 in Research Square
Verified
Preprint
Open access
SPSowbhagya S Prabhu
Sowbhagya S Prabhu
JSJeevanand E S
Jeevanand E S
SVSwapna V
Swapna V
The classical Pareto distribution is a foundational model for the heavy-tailed phenomena, particularly in reliability analysis, where the Total Time on Test (TTT) transform serves as a key measure. However, conventional estimation techniques for the TTT transform, such as those based on Maximum Likelihood, are sample-sensitive and biased, especially in small samples, which are common challenges with heavy-tailed data. To address these limitations, the present study proposes a robust estimation framework based on Quasi-Bayesian methodology. The estimators are derived under both Gamma and Jeffrey’s priors, and with symmetric Squared Error and asymmetric loss functions to accommodate diverse inferential objectives. To further enhance estimator stability and mitigate overfitting, the shrinkagebased technique and penalization via L1 (Lasso-type) and L2 (Quadratic) are introduced. The performance of these novel estimators is systematically evaluated against classical methods and Thompson-type shrinkage estimators via a comprehensive Monte Carlo simulation study. The results demonstrate the superior finite-sample properties, in terms of bias and Mean Squared Error(MSE), of the proposed regularized and shrinkage estimators, particularly in small-sample settings. An application to a real-world insurance claims dataset illustrates the practical implications and utility of our proposed methodologies for risk assessment.