Abstract
In this paper, we consider some objective priors for the ratio of variabilities in a bivariate normal distribution. We develop the first and second order matching priors and reference priors. We obtain that the second order matching prior matches the alternative coverage probabilities up to the same order. It is also an HPD matching priors. It turns out that the derived reference priors do not satisfy a second order matching criterion. The simulation result shows that the second order matching prior performs better than reference priors based on matching the target coverage probabilities in a frequentist sense. Finally, we show that the second order matching prior and reference priors produce confidence sets with an expected length shorter than the Cox and Reid adjustment.
Similar content being viewed by others
References
Berger, J. O., & Bernardo, J. M. (1989). Estimating a product of means: Bayesian analysis with reference priors. Journal of the American Statistical Association, 84, 200–207.
Berger, J. O., & Bernardo, J. M. (1992). On the development of reference priors (with discussion). In J. M. Bernardo, et al. (Eds.), Bayesian Statistics IV (pp. 35–60). Oxford University Press.
Bernardo, J. M. (1979). Reference posterior distributions for Bayesian inference (with discussion). Journal of Royal Statistical Society B, 41, 113–147.
Box, G. E. P. & Tiao, G. C. (1973). Bayesian Inference in Statistical Analysis. Addison-Wesley.
Brown, L. D. (1968). Inadmissibility of the usual estimators of scale parameters. Annals of Mathematical Statistics, 39, 29–48.
Cox, D. R., & Reid, N. (1987). Orthogonal parameters and approximate conditional inference (with discussion). Journal of Royal Statistical Society B, 49, 1–39.
Datta, G. S. (1996). On priors providing frequentist validity for Bayesian inference. Biometrika, 83, 287–298.
Datta, G. S., & DiCiccio, T. J. (2001). On expected volumes of multidimensional confidence sets associated with the usual and adjusted likelihoods. Journal of Royal Statistical Society B, 63, 691–703.
Datta, G. S., & Ghosh, J. K. (1995). On priors providing frequentist validity for Bayesian inference. Biometrika, 82, 37–45.
Datta, G. S., & Ghosh, M. (1995). Some remarks on noninformative priors. Journal of the American Statistical Association, 90, 1357–1363.
Datta, G. S., & Ghosh, M. (1996). On the invariance of noninformative priors. The Annal of Statistics, 24, 141–159.
Datta, G. S., Ghosh, M., & Mukerjee, R. (2000). Some new results on probability matching priors. Calcutta Statistical Association Bulletin, 50, 179–192.
Datta, G. S., & Mukerjee, R. (2004). Probability Matching Priors: Higher Order Asymptotics. Springer.
DiCiccio, T. J., & Stern, S. E. (1994). Frequentist and Bayesian Bartlett correction of test statistics based on adjusted profile likelihood. Journal of Royal Statistical Society B, 56, 397–408.
Gelfand, A. E., & Dey, D. K. (1988). On estimation of a variance ratio. Journal of Statistical Planning and Inference, 19, 121–131.
Ghosh, M., & Kundu, S. (1996). Decision theoretic estimation of the variance ratio. Statistics & Decisions, 14, 161–175.
Ghosh, J. K., & Mukerjee, R. (1995). Frequentist validity of highest posterior density regions in the presence of nuisance parameters. Statistics & Decisions, 13, 131–139.
Iliopoulos, G. (2001). Decision theoretic estimation of the ratio of variances in a bivariate normal distribution. Annals of Institute of Statistical Mathematics, 53, 436–446.
Kim, D. H., Kang, S. G., & Cho, J. S. (2000). Noninformative priors for stress-strength system in the Burr-type X model. Journal of the Korean Statistical Society, 29, 17–27.
Kim, Y., Lee, W. D., & Kang, S. G. (2020). A matching prior based on the modified profile likelihood for the common mean in multiple log-normal distributions. Statistical Papers, 61, 543–573.
Kim, D. H., Lee, W. D., Kang, S. G., & Kim, Y. (2019). Noninformative priors for the between-group variance in the unbalanced one-way random effects model with heterogeneous error variances. Journal of Statistical Computation and Simulation, 89, 1935–1956.
Madi, T. M. (1995). On invariant estimation of a normal variance ratio. Journal of Statistical Planning and Inference, 44, 349–357.
Min, X., & Sun, D. (2013). A matching prior based on the modified profile likelihood in a generalized Weibull stress-strength model. The Canadian Journal of Statistics, 41, 83–97.
Morgan, W. A. (1939). A test for the significance of the difference between the two variances in a sample from a normal bivariate population. Biometrika, 31, 13–19.
Mukerjee, R., & Dey, D. K. (1993). Frequentist validity of posterior quantiles in the presence of a nuisance parameter: Higher order asymptotics. Biometrika, 80, 499–505.
Mukerjee, R., & Ghosh, M. (1997). Second order probability matching priors. Biometrika, 84, 970–975.
Mukerjee, R., & Reid, N. (1999a). On a property of probability matching priors: Matching the alternative coverage probabilities. Biometrika, 86, 333–340.
Mukerjee, R., & Reid, N. (1999b). On confidence intervals associated with the usual and adjusted likelihoods. Journal of Royal Statistical Society B, 61, 945–954.
Stein, C. (1964). Inadmissibility of the usual estimator for the variance of a normal distribution with unknown mean. Annals of the Institute of Statistical Mathematics, 42, 385–388.
Stein, C. (1985). On the coverage probability of confidence sets based on a prior distribution. Sequential Methods in Statistics, Banach Center Publications, 16, 485–514.
Tibshirani, R. (1989). Noninformative priors for one parameter of many. Biometrika, 76, 604–608.
Ventura, L., Cabras, S., & Racugno, W. (2009). Prior distributions from pseudo-likelihoods in the presence of nuisance parameters. Journal of the American Statistical Association, 104, 768–774.
Wang, W. (1999). On equivalence of two variances of a bivariate normal vector. Journal of Statistical Planning and Inference, 81, 279–292.
Welch, B. L., & Peers, H. W. (1963). On formulae for confidence points based on integrals of weighted likelihood. Journal of Royal Statistical Society, B, 35, 318–329.
Acknowledgements
This Research was supported by Kyungpook National University Research Fund, 2020.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix 1. Proof of impropriety of posterior distribution
The posterior distribution of \((\theta _1,\ldots ,\theta _5)\) under the prior \(\pi (\theta _1,\ldots ,\theta _5)=\theta _1^{-1}\theta _2^{-1}\theta _3^{-1}\) is improper.
Proof
Under the prior \(\pi (\theta _1,\ldots ,\theta _5)=\theta _1^{-1}\theta _2^{-1}\theta _3^{-1}\), the joint posterior for \(\theta _1,\ldots ,\theta _5\) given \(\mathbf{Y}\) is
By integrating with respect to \(\theta _4\) and \(\theta _5\), we obtain
where \(c_1\) is a constant. Let \(\theta _1={\sigma _2 \over \sigma _1}\), \(\theta _2=\rho \sigma _1 \sigma _2\), and \(\theta _3= \sigma _1^2 \sigma _2^2 (1-\rho ^2)\). Then
where \(c_2\) is a constant. Let \(u={\sigma _1\sigma _2 \over S_1S_2}\) and \(v={\sigma _1/S_1 \over \sigma _2/S_2}\). Then, the above integral reduces to
where \(c_3\) is a constant and \(r={S_{12}\over S_1S_2}\). Thus, if \(n-1>0\), then upon integrating out u,
where \(c_4\) is a constant. Let \(z={{1\over 2}[v+(1/v)]-1\over {1\over 2}[v+(1/v)]-\rho r}\). Then, the above integral implies
where \(c_5\) and \(c_6\) are constants, and H is a hypergeometric function. The last integral does not converge on \((-1,1)\) because of \(\rho ^{-1}\). This completes the proof. \(\square \)
Apprndix 2. Derivation of reference prior
In this appendix, we derive the reference prior for the parameter grouping \(\{ \theta _1, \theta _3, \theta _2, \theta _4, \theta _5 \}\). We follow the algorithm given by Berger and Bernardo (1992).
The reference prior is developed by considering a sequence of compact subsets of the parameter space, and taking the limit of a sequence of priors as these compact subsets fill out the parameter space. The compact subsets were taken to be Cartesian products of sets of the form
Suppose the limit \(a_1, a_3\) tend to 0, then \(a_2, a_4, a_5\) will tend to \(-\infty \), and \(b_1, b_2, b_3, b_4, b_5\) will tend to \(\infty \). For the derivation of the reference, from the inverse of the Fisher information, we obtain
In what follows, a subscripted K denotes a constant function independent of any parameters. However, any K may depend on the ranges of the parameters.
Step 1. Note that
so \(\pi _5^l \{\theta _5 \vert \theta _1,\theta _3,\theta _2,\theta _4\}=K_1\), where \(K_1=(b_5-a_5)^{-1}\).
Step 2. Now,
It follows that
Hence,
Step 3. Now,
Therefore,
Thus
Step 4. Now,
It follows that
Hence,
where \(K_5=K_3/\log \left\{ {b_3\over a_3}\right\} \).
Step 5. Now,
So,
Then,
where \(K_8=K_5{\exp \{K_6/2 \}\over K_7 \log \{{b_1/ a_1}\}}\). Therefore, the prior reference is given by
Rights and permissions
About this article
Cite this article
Kim, D.H., Kang, S.G., Lee, W.D. et al. Noninformative priors for the ratio of variabilities in a bivariate normal population. J. Korean Stat. Soc. 50, 874–890 (2021). https://doi.org/10.1007/s42952-021-00119-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42952-021-00119-3