pith. sign in

arxiv: 2604.12130 · v1 · submitted 2026-04-13 · 📊 stat.ME · math.ST· stat.AP· stat.CO· stat.TH

Reliability estimation in dependent stress-strength model with Clayton copula and modified Weibull margins

Fatih K{\i}z{\i}laslan This is my paper

Pith reviewed 2026-05-10 14:48 UTC · model grok-4.3

classification 📊 stat.ME math.STstat.APstat.COstat.TH
keywords stress-strength reliabilityClayton copulamodified Weibull distributiondependent variablesreliability estimationMonte Carlo simulationbootstrap confidence intervals
0
0 comments X

The pith

Stress-strength reliability is estimated via a seven-parameter model with modified Weibull distributions and Clayton copula dependence.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper develops a stress-strength reliability model that incorporates dependence between the stress and strength variables. Both margins follow modified Weibull distributions while a Clayton copula captures their joint behavior, yielding a flexible seven-parameter structure. Several estimation procedures are introduced and compared through Monte Carlo simulations under varied settings. The model is then fitted to monthly occupancy records from two Istanbul dams to demonstrate practical use in water management decisions.

Core claim

The authors construct and analyze a dependent stress-strength reliability model in which stress and strength each follow a modified Weibull distribution and are linked by a Clayton copula. Distinct parameter vectors for the two margins produce a seven-parameter family. Estimation is performed by two-step maximum likelihood, ordinary and weighted least squares, and maximum product of spacings, with asymptotic and bootstrap intervals supplied for inference. Finite-sample behavior is examined in extensive simulations, and the model is applied to real dam-occupancy data.

What carries the argument

Seven-parameter structure formed by two modified Weibull margins joined by a Clayton copula that encodes the dependence between stress and strength.

If this is right

  • Reliability can be quantified when stress and strength are dependent rather than independent.
  • Several competing estimators and interval methods are available and can be chosen according to sample size and parameter regime.
  • The estimated reliability supplies a numerical basis for operational decisions such as water-release scheduling between dams.
  • Bootstrap intervals offer a practical alternative when asymptotic approximations are unreliable.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same copula-margin construction could be reused for other pairs of dependent lifetime variables once suitable marginal families are identified.
  • Replacing the Clayton copula with alternative dependence models would allow direct comparison of how different dependence structures affect reliability estimates.
  • If the seven-parameter model proves stable, it could serve as a baseline for testing whether additional covariates or time-varying dependence improve predictive accuracy in engineering reliability problems.

Load-bearing premise

The Clayton copula correctly represents the dependence between stress and strength and the modified Weibull distributions fit the marginal data in both simulated and observed settings.

What would settle it

A simulation in which the true dependence structure differs from the Clayton copula and the resulting confidence-interval coverage falls well below nominal levels, or a formal goodness-of-fit test on the dam data that rejects either the modified Weibull margins or the Clayton copula.

Figures

Figures reproduced from arXiv: 2604.12130 by Fatih K{\i}z{\i}laslan.

Figure 1
Figure 1. Figure 1: Bias and MSE of the copula parameter θ and the stress-strength reliability R [PITH_FULL_IMAGE:figures/full_fig_p016_1.png] view at source ↗
read the original abstract

Stress-strength models are widely used to assess the reliability of systems under uncertain conditions. While most studies assume independence between stress and strength variables, such an assumption may be unrealistic in many practical situations where these components are inherently dependent. In this study, we investigate stress-strength reliability under a dependent framework, where both stress and strength variables follow modified Weibull distributions and their dependence is modeled via a Clayton copula. The proposed model allows distinct parameter sets, resulting in a flexible seven-parameter structure that extends Weibull-based models. We consider several estimation procedures for the model parameters and reliability, including two-step maximum likelihood, least squares, weighted least squares, and maximum product of spacings, with interval estimation obtained via asymptotic and bootstrap confidence intervals. The performance of the proposed estimators is evaluated through an extensive Monte Carlo simulation study under various parameter configurations and sample sizes. Finally, the applicability of the proposed model is illustrated using monthly occupancy data from Istanbul's two largest dams, with the Clayton copula capturing their dependence structure. This application demonstrates how stress-strength reliability can inform water management decisions and mitigate inter-regional operational risks.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper proposes a seven-parameter dependent stress-strength reliability model in which stress and strength each follow a modified Weibull distribution and their joint distribution is specified by a Clayton copula. It derives the reliability function R = P(Y > X), presents four estimation procedures (two-step MLE, least squares, weighted least squares, maximum product of spacings) together with asymptotic and bootstrap interval estimators, evaluates finite-sample performance via Monte Carlo simulation across parameter settings and sample sizes, and illustrates the model on monthly occupancy series from two Istanbul dams.

Significance. If the dependence structure is adequately captured, the model supplies a flexible, non-identical-margin extension of earlier Weibull-based stress-strength frameworks that can be applied to correlated reliability problems such as water-resource management. The multi-estimator comparison and simulation design are positive features that allow readers to assess practical performance.

major comments (2)
  1. [Application section (Istanbul dam data)] Application section (Istanbul dam data): no copula goodness-of-fit diagnostic (Rosenblatt residuals, Cramér-von Mises or Kolmogorov-Smirnov statistic against the empirical copula, or formal comparison with Frank/Gumbel alternatives) is reported for the fitted Clayton copula. Because the Clayton family imposes lower-tail dependence only, the absence of such verification leaves the central claim that the model is applicable to the dam occupancy data unsupported.
  2. [§4 (Monte Carlo study)] §4 (Monte Carlo study): the reported bias and MSE tables do not include coverage probabilities or interval lengths for the bootstrap confidence intervals under the seven-parameter setting; without these quantities it is impossible to judge whether the interval estimators achieve nominal coverage when dependence is present.
minor comments (2)
  1. [Model definition] The modified Weibull cdf and pdf are introduced without an explicit equation number; subsequent references to the parameters would be clearer if the functional form were labeled (e.g., Eq. (2)).
  2. [Tables in §4] Table captions should state the sample sizes and true parameter vectors used in each simulation scenario.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed review of our manuscript. We have addressed each major comment below and will incorporate the suggested additions in the revised version to strengthen the presentation of the copula fit and the simulation results.

read point-by-point responses

  1. Referee: Application section (Istanbul dam data): no copula goodness-of-fit diagnostic (Rosenblatt residuals, Cramér-von Mises or Kolmogorov-Smirnov statistic against the empirical copula, or formal comparison with Frank/Gumbel alternatives) is reported for the fitted Clayton copula. Because the Clayton family imposes lower-tail dependence only, the absence of such verification leaves the central claim that the model is applicable to the dam occupancy data unsupported.

    Authors: We agree that a formal goodness-of-fit assessment is required to substantiate the use of the Clayton copula for the dam occupancy data. In the revised manuscript we will report the Cramér-von Mises statistic computed from the empirical copula and the associated p-value, together with Rosenblatt residuals plotted against the uniform distribution. We will also add a short comparison of Clayton with the Frank and Gumbel copulas using both the goodness-of-fit statistics and the maximized log-likelihood values, thereby justifying the selection on the basis of lower-tail dependence that is plausible for joint low-occupancy periods. revision: yes

  2. Referee: §4 (Monte Carlo study): the reported bias and MSE tables do not include coverage probabilities or interval lengths for the bootstrap confidence intervals under the seven-parameter setting; without these quantities it is impossible to judge whether the interval estimators achieve nominal coverage when dependence is present.

    Authors: We acknowledge that the simulation tables currently emphasize point-estimator performance. To enable evaluation of the interval estimators, the revised Monte Carlo study will include coverage probabilities and mean interval lengths for the bootstrap confidence intervals of the reliability parameter R under the full seven-parameter model, reported for each combination of sample size and dependence strength already considered in the bias/MSE tables. revision: yes

Circularity Check

0 steps flagged

No circularity: standard parametric modeling with data-driven estimation

full rationale

The paper defines a joint distribution for stress and strength using modified Weibull marginals (with distinct parameter sets) and a Clayton copula, then estimates the seven parameters via two-step MLE, least squares, and other standard methods before computing the reliability R = P(X > Y) under the fitted joint. This chain does not reduce R to a fitted value by construction, nor does it rely on self-citations for uniqueness or load-bearing premises; the simulation study separately validates estimator performance under known parameters, and the dam-data application simply plugs the fitted model into the reliability integral without tautological redefinition. No step matches the enumerated circularity patterns.

Axiom & Free-Parameter Ledger

1 free parameters · 2 axioms · 0 invented entities

The central claim rests on the selection of modified Weibull as marginals and Clayton copula for dependence, which are standard choices but introduce several fitted parameters without new theoretical justification beyond flexibility.

free parameters (1)
  • seven model parameters
    Includes parameters for the two modified Weibull distributions (typically location, scale, shape, and modification terms) plus the copula dependence parameter, all estimated from data.
axioms (2)
  • domain assumption Stress and strength follow modified Weibull distributions
    Invoked as the marginal distributions in the model setup.
  • domain assumption Dependence structure is captured by Clayton copula
    Chosen to model the joint behavior of stress and strength.

pith-pipeline@v0.9.0 · 5500 in / 1388 out tokens · 70384 ms · 2026-05-10T14:48:35.316738+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

29 extracted references · 29 canonical work pages

  1. [1]

    Birnbaum

    Z.W. Birnbaum. On a use of the Mann-Whitney statistic. In Proceedings of the Third Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Contributions to the Theory of Statistics, volume 3, pages 13--18. University of California Press, 1956

    work page 1956

  2. [2]

    Birnbaum and R.C

    Z.W. Birnbaum and R.C. McCarty. A distribution-free upper confidence bound for Pr(Y<X) , based on independent samples of X and Y . The Annals of Mathematical Statistics, pages 558--562, 1958

    work page 1958

  3. [3]

    The stress--strength model and its generalizations: theory and applications

    Samuel Kotz, Yan Lumelskii, and Marianna Pensky. The stress--strength model and its generalizations: theory and applications. World Scientific, New Jersey, 2003

    work page 2003

  4. [4]

    A copula-based approach to account for dependence in stress-strength models

    Filippo Domma and Sabrina Giordano. A copula-based approach to account for dependence in stress-strength models. Statistical Papers, 54 0 (3): 0 807--826, 2013

    work page 2013

  5. [5]

    A stress--strength model with dependent variables to measure household financial fragility

    Filippo Domma and Sabrina Giordano. A stress--strength model with dependent variables to measure household financial fragility. Statistical Methods & Applications, 21 0 (3): 0 375--389, 2012

    work page 2012

  6. [6]

    Estimation of reliability in a multicomponent stress--strength model based on a bivariate Kumaraswamy distribution

    Fatih K z laslan and Mustafa Nadar. Estimation of reliability in a multicomponent stress--strength model based on a bivariate Kumaraswamy distribution. Statistical Papers, 59: 0 307--340, 2018

    work page 2018

  7. [7]

    Reliability for some bivariate beta distributions

    Saralees Nadarajah. Reliability for some bivariate beta distributions. Mathematical Problems in Engineering, 2005 0 (1): 0 101--111, 2005

    work page 2005

  8. [8]

    Reliability for some bivariate exponential distributions

    Saralees Nadarajah and Samuel Kotz. Reliability for some bivariate exponential distributions. Mathematical Problems in Engineering, 2006 0 (1): 0 041652, 2006

    work page 2006

  9. [9]

    Estimation of reliability in a multicomponent stress-strength model based on a Marshall-Olkin bivariate Weibull distribution

    Mustafa Nadar and Fatih K z laslan. Estimation of reliability in a multicomponent stress-strength model based on a Marshall-Olkin bivariate Weibull distribution. IEEE Transactions on Reliability, 65 0 (1): 0 370--380, 2015

    work page 2015

  10. [10]

    Reliability estimation of multicomponent stress--strength model based on copula function under progressively hybrid censoring

    Xuchao Bai, Yimin Shi, Yiming Liu, and Bin Liu. Reliability estimation of multicomponent stress--strength model based on copula function under progressively hybrid censoring. Journal of Computational and Applied Mathematics, 344: 0 100--114, 2018

    work page 2018

  11. [11]

    Reliability estimation of s-out-of-k system in a multicomponent stress--strength dependent model based on copula function

    Tiefeng Zhu. Reliability estimation of s-out-of-k system in a multicomponent stress--strength dependent model based on copula function. Journal of Computational and Applied Mathematics, 404: 0 113920, 2022

    work page 2022

  12. [12]

    Reliability analysis of s-out-of-k multicomponent stress-strength system with dependent strength elements based on copula function

    Jing Cai, Jianfeng Yang, and Yongjin Zhang. Reliability analysis of s-out-of-k multicomponent stress-strength system with dependent strength elements based on copula function. Mathematical Biosciences and Engineering, 20 0 (5): 0 9470--9488, 2023

    work page 2023

  13. [13]

    Reliability estimation stress--strength dependent model based on copula function using ranked set sampling

    Li-feng Shang and Zai-zai Yan. Reliability estimation stress--strength dependent model based on copula function using ranked set sampling. Journal of Radiation Research and Applied Sciences, 17 0 (1): 0 100811, 2024

    work page 2024

  14. [14]

    Bayesian inference for dependent stress--strength reliability of series--parallel system based on copula

    Li Zhang, Rongfang Yan, and Junrui Wang. Bayesian inference for dependent stress--strength reliability of series--parallel system based on copula. Scientific Reports, 15 0 (1): 0 29504, 2025

    work page 2025

  15. [15]

    Copula-based reliability estimation of parallel-series system in the multicomponent stress--strength dependent model

    Li Zhang and Rongfang Yan. Copula-based reliability estimation of parallel-series system in the multicomponent stress--strength dependent model. Probability in the Engineering and Informational Sciences, 39 0 (3): 0 309--325, 2025

    work page 2025

  16. [16]

    A modified W eibull distribution

    Chin-Diew Lai, Min Xie, and D.N.P Murthy. A modified W eibull distribution. IEEE Transactions on Reliability, 52 0 (1): 0 33--37, 2003

    work page 2003

  17. [17]

    Soliman, A.H

    Ahmed A. Soliman, A.H. Abd-Ellah, N.A. Abou-Elheggag, and Essam A. Ahmed. Reliability estimation in stress--strength models: an MCMC approach. Statistics, 47 0 (4): 0 715--728, 2013

    work page 2013

  18. [18]

    Estimation of P(Y< X) for modified W eibull distribution under progressive Type-II censoring

    Reetu Goel and Bhupendra Singh. Estimation of P(Y< X) for modified W eibull distribution under progressive Type-II censoring. Life Cycle Reliability and Safety Engineering, 9 0 (3): 0 227--240, 2020

    work page 2020

  19. [19]

    Roger B. Nelsen. An Introduction to Copulas. Springer, 2006

    work page 2006

  20. [20]

    R: A Language and Environment for Statistical Computing

    R Core Team . R: A Language and Environment for Statistical Computing . R Foundation for Statistical Computing, Vienna, Austria, 2024. URL https://www.R-project.org/

    work page 2024

  21. [21]

    u lce C \

    G \"u lce C \"u ran and Fatih K z laslan. Statistical inference on stress-strength reliability for the Marshall-Olkin family of distributions. Soft Computing, 30: 0 189–208, 2026

    work page 2026

  22. [22]

    Statistical modelling and inference for multivariate and longitudinal discrete response data

    James Jianmeng Xu. Statistical modelling and inference for multivariate and longitudinal discrete response data. PhD thesis, University of British Columbia, 1996

    work page 1996

  23. [23]

    The estimation method of inference functions for margins for multivariate models

    Harry Joe and James Jianmeng Xu. The estimation method of inference functions for margins for multivariate models. Technical Report 166, Department of Statistics, University of British Columbia, 1996

    work page 1996

  24. [24]

    Asymptotic efficiency of the two-stage estimation method for copula-based models

    Harry Joe. Asymptotic efficiency of the two-stage estimation method for copula-based models. Journal of multivariate Analysis, 94 0 (2): 0 401--419, 2005

    work page 2005

  25. [25]

    Jiang, M

    H. Jiang, M. Xie, and L.C. Tang. On mles of the parameters of a modified W eibull distribution for progressively type-2 censored samples. Journal of Applied Statistics, 37 0 (4): 0 617--627, 2010

    work page 2010

  26. [26]

    Vidyadhar P. Godambe. An optimum property of regular maximum likelihood estimation. The Annals of Mathematical Statistics, 31 0 (4): 0 1208--1211, 1960

    work page 1960

  27. [27]

    Swain, Sekhar Venkatraman, and James R

    James J. Swain, Sekhar Venkatraman, and James R. Wilson. Least-squares estimation of distribution functions in J ohnson's translation system. Journal of Statistical Computation and Simulation, 29 0 (4): 0 271--297, 1988

    work page 1988

  28. [28]

    Cheng and N.A.K

    R.C.H. Cheng and N.A.K. Amin. Estimating parameters in continuous univariate distributions with a shifted origin. Journal of the Royal Statistical Society: Series B (Methodological), 45 0 (3): 0 394--403, 1983

    work page 1983

  29. [29]

    u l Akg \

    Fatma G \"u l Akg \"u l. Estimation of multicomponent stress--strength reliability based on unit Burr XII distribution: an application to dam occupancy rate of Istanbul, Turkey . Journal of Statistical Computation and Simulation, 93 0 (18): 0 3217--3234, 2023

    work page 2023