Hypothesis testing and interval estimation for quantiles in a bivariate normal setup with a common mean

Year 2025, Volume: 54 Issue: 5, 2007 - 2035, 29.10.2025

Habiba Khatun , Manas Tripathy , Nabendu Pal

https://doi.org/10.15672/hujms.1619950

Abstract

This article deals with hypothesis testing and interval estimation of a quantile in a bivariate normal population with a common mean setup. We consider independent and identically distributed random samples from a bivariate normal population with an unknown common mean $\mu,$ unknown variances $\sigma_{1}^2$ and $\sigma_{2}^2,$ and an unknown correlation coefficient $\rho.$ First, we derive an asymptotic confidence interval, followed by a classical confidence interval using the method of recovery of the variance estimate. We also develop approximate confidence intervals, including the bootstrap-p, bootstrap-t, and highest posterior density intervals. Additionally, we obtain two generalized confidence intervals utilizing some estimators of the common mean. Before addressing the hypothesis testing regarding the target quantile, we first tested the equality of the quantiles for two marginal distributions. We derive several tests for this hypothesis testing problem, including the likelihood ratio test, tests based on computational approaches, and tests based on the generalized variable method. An extensive simulation study has been carried out to demonstrate the performance of the proposed tests and interval estimates. The interval estimators are assessed on the basis of their coverage probability and average length, while the tests are evaluated according to their size and power values. Finally, the article concludes with two real-life examples demonstrating the potential applications of the proposed methods.

Keywords

Asymptotic confidence interval , bootstrap-p , bootstrap-t , computational approach , generalized p-value , bootstrap likelihood ratio test , size and power analysis

Supporting Institution

The second author (Manas Ranjan Tripathy) would like to thank Science and Engineering Research Board (SERB), Department of Science and Technology (DST) (CRG/ 2023/002586), New Delhi, India, for providing some financial support.

Thanks

The authors would like to thank all the anonymous reviewers and the editor for their constructive suggestions and comments which have improved the manuscript. The second author (Manas Ranjan Tripathy) would like to thank Science and Engineering Research Board (SERB), Department of Science and Technology (DST) (CRG/2023/002586), New Delhi, India, for providing some financial support.

References

• [1] N. Balakrishnan and J.-A. Kim, Point and interval estimation for bivariate normal distribution based on progressively type-II censored data, Communications in Statistics— Theory and Methods, 34 (6), 1297–1347, 2005.
• [2] I. Bebu and T. Mathew, Comparing the means and variances of a bivariate log-normal distribution, Statistics in Medicine, 27 (14), 2684–2696, 2008.
• [3] G.E. Box and G.C. Tiao, Bayesian inference in statistical analysis, John Wiley and Sons, 2011.
• [4] M. Chacko and S. Mathew, Inference on P(X < Y ) for bi-variate normal distribution based on ranked set sample, Metron„ 77 (3), 239–252, 2019.
• [5] C.H. Chang, N. Pal and J.-J. Lin, A revisit to test the equality of variances of several populations, Communications in Statistics-Simulation and Computation 46 (8), 6360–6384, 2017.
• [6] M.H. Chen and Q.-M. Shao, Monte carlo estimation of Bayesian credible and HPD intervals, Journal of Computational and Graphical Statistics, 8 (1), 69-92, 2017.
• [7] S. Chib and E. Greenberg, ıUnderstanding the Metropolis-Hastings algorithm, The American Statistician, 49 (4), 327-335, 1995.
• [8] T.J. Diciccio, M.A. Martin and S.E. Stern, Simple and accurate one-sided inference from signed roots of likelihood ratios, Canadian Journal of Statistics, 29 (1), 67–76, 2001.
• [9] B. Efron, The Jackknife, the Bootstrap, and other Resampling Plans, 38, SIAM, Philadelphia. 1982.
• [10] A.E. Gelfand, Gibbs sampling, Journal of the American Statistical Association, 95 (452), 1300-1304, 2000.
• [11] R.C. Gupta, M. Ghitany and D. Al-Mutairi, Estimation of reliability from a bivariate log-normal data, Journal of Statistical Computation and Simulation, 83 (6), 1068–1081, 2013.
• [12] P. Hall and M.A. Martin, On bootstrap re-sampling and iteration, Biometrika, 75 (4), 661–671, 1988.
• [13] M. Halperin, Almost linearly-optimum combination of unbiased estimates, Journal of the American Statistical Association, 56 (293), 36–43, 1961.
• [14] J.A. Hanley, Transmuting women into men: Galton’s family data on human stature, The American Statistician, 58 (3), 237–243, 2004.
• [15] D.M. Hawkins, Diagnostics for conformity of paired quantitative measurements, Statistics in Medicine, 21 (13), 1913–1935, 2002.
• [16] N. Jana and M. Gautam, Interval estimation of the common mean and difference of medians for a bi-variate log-normal distribution, Journal of Statistical Computation and Simulation, 92 (15), 3249-3274, 2022.
• [17] H. Khatun, M.R. Tripathy and N. Pal, Hypothesis testing and interval estimation for quantiles of two normal populations with a common mean, Communications in Statistics - Theory and Methods, 51 (16), 5692–5713, 2020.
• [18] K. Krishnamoorthy and V.K. Rohatgi, Estimation of the common mean of a bivariate normal distribution, Journal of Statistical Computation and Simulation, 31 (3), 187–194, 1989.
• [19] S. Kumar and D. Sharma, Estimating the common mean of a bivariate normal population, Australian Journal of Statistics, 34 (1), 39–46, 1992.
• [20] S. Kumar and M.R. Tripathy, Estimating quantiles of normal populations with a common mean, Communications in Statistics-Theory and Methods, 40 (15), 2719–2736, 2011.
• [21] R.J. Muirhead, Aspects of multivariate statistical theory, John Wiley and Sons, 2009.
• [22] N. Nagamani and M.R. Tripathy, Improved estimation of quantiles of two normal populations with common mean and ordered variances, Communications in Statistics- Theory and Methods, 49 (19), 4669-4692, 2019.
• [23] N. Pal, W.K. Lim and C.-H. Ling, A computational approach to statistical inferences, Journal of Applied Probability and Statistics, 2 (1), 13–35, 2007.
• [24] C.P. Robert and G. Casella, Monte Carlo Statistical Methods, 2, 1999, Springer New York.
• [25] A.L. Rukhin, A class of minimax estimators of a normal quantile, Statistics and Probability Letters, 1 (5), 217–221, 1983.
• [26] N. Sunthornworasiri, M. Tiensuwan and B.K. Sinha, Statistical inference for a bivariate normal population with a common mean, International Journal of Statistical Sciences, 5, 9–26, 2006.
• [27] M.R. Tripathy and S. Kumar, Estimating common mean of a bivariate normal population with order restricted variances, Calcutta Statistical Association Bulletin, 63 (1-4), 157–180, 2011.
• [28] M.R. Tripathy and S. Kumar, Equivariant estimation of common mean of several normal populations, Journal of Statistical Computation and Simulation, 85 (18), 3679-3699, 2015.
• [29] M.R. Tripathy, S. Kumar and A.K. Jena, Estimating quantiles of several normal populations with a common mean, Communications in Statistics-Theory and Methods, 46 (11), 5656–5671, 2017.
• [30] K.-W. Tsui and S. Weerahandi, Generalized p-values in significance testing of hypotheses in the presence of nuisance parameters, Journal of the American Statistical Association, 84 (406), 602–607, 1989.
• [31] S. Weerahandi, Generalized confidence intervals, Journal of the American Statistical Association, 88 (423), 899-906, 1993.
• [32] J.V. Zidek, Inadmissibility of the best invariant estimator of extreme quantiles of the normal law under squared error loss, The Annals of Mathematical Statistics, 40 5, 1801–1808, 1969.
• [33] J.V. Zidek, Inadmissibility of a class of estimators of a normal quantile, The Annals of Mathematical Statistics, 42 (4), 1444–1447, 1971.
• [34] G. Zou, C.Y. Huo and J. Taleban, Simple confidence intervals for lognormal means and their differences with environmental applications, Environmetrics: The official Journal of the International Environmetrics Society, 20 (2), 172–180, 2009.