On Analysis of the Behrens-Fisher Problem Based on Bayesian Evidence

DOI: 10.4236/ojs.2019.91001   PDF   HTML     372 Downloads   536 Views  


In this paper we have demonstrated the ability of the new Bayesian measure of evidence of Yin (2012, Computational Statistics, 27: 237-249) to solve both the Behrens-Fisher problem and Lindley's paradox. We have provided a general proof that for any prior which yields a linear combination of two independent t random variables as posterior distribution of the di erence of means, the new Bayesian measure of evidence given that prior will solve Lindleys' paradox thereby serving as a general proof for the works of Yin and Li (2014, Journal of Applied Mathematics, 2014(978691)) and Goltong and Doguwa (2018, Open Journal of Statistics, 8: 902-914). Using the Pareto prior as an example, we have shown by the use of simulation results that the new Bayesian measure of evidence solves Lindley's paradox.

Share and Cite:

Goltong, N. and Doguwa, S. (2019) On Analysis of the Behrens-Fisher Problem Based on Bayesian Evidence. Open Journal of Statistics, 9, 1-14. doi: 10.4236/ojs.2019.91001.

Conflicts of Interest

The authors declare no conflicts of interest.


[1] Lindley, D.-V. (1957) A Statistical Paradox. Biometrika, 44, 187-192.
[2] Robert, C.-P. (2014) On the Je_reys-Lindley Paradox. Philosophy of Science, 81, 216-232.
[3] Sprenger, J. (2013) Testing a Precise Null Hypothesis: The Case of Lindleys Paradox. Philosophy of Science, 80, 733-744.
[4] Spanos, A. (2013) Who Should Be Afraid of the Je_reys-Lindley Paradox? Philosophy of Science, 80, 73-93.
[5] Yin, Y. (2012) A New Bayesian Procedure for Testing Point Null Hypotheses. Computational Statistics, 27, 237-249.
[6] Yin, Y. and Li, B. (2014) Analysis of the Behrens-Fisher Problem Based on Bayesian Evidence. Journal of Applied Mathematics, 2014, Article ID: 978691.
[7] Goltong, N.-E. and Doguwa, S.-I. (2018) Bayesian Analysis of the Behrens-Fisher Problem under a Gamma Prior. Open Journal of Statistics, 8, 902-914.
[8] Tsui, K.-W. and Weerahandi, S. (1989) Generalized p-Values in Signi_cance Testing of Hypotheses in the Presence of Nuisance Parameters. Journal of the American Statistical Association, 84, 602-607.
[9] Iyer, H.-K. and Paterson, P.-D. (2002) A Recipe for Constructing Generalized Pivotal Quantities and Generalized Con_dence Intervals. Technical Report 2002/10, Department of Statistics, Colorado State University, Fort Collins.
[10] Mitra, P.-K. and Sinha, B.-K. (2007) A Generalized p-Value Approach to Inference on Common Mean. Technical Report, Department of Mathematics and Statistics, University of Maryland, Baltimore.
[11] Zheng, S., Shi, N.-Z. and Ma, W. (2010) Statistical Inference on Di_erence or Ratio of Means from Heteroscedastic Normal Populations. Journal of Statistical Planning and Inference, 140, 1236-1242.
[12] Ozkip, E., Yazici, B. and Sezer, A. (2014) A Simulation Study on Tests for the Behrens-Fisher Problem. Turkiye Klinikleri Journal of Biostatistics, 6, 59-66.
[13] Degroot, M.-H. (1982) Comment. Journal of the American Statistical Association, 77, 336-339.
[14] Berger, J.-O. and Selke, T. (1987) Testing a Point Null Hypothesis: The Irreconcilability of p Values and Evidence. Journal of the American Statistical Association, 82, 112-122.
[15] Casella, G. and Berger, R.-L. (1987) Reconciling Bayesian and Frequentist Evidence in One-Sided Testing Problem. Journal of the American Statistical Association, 82, 106-111.
[16] Berger, J.-O. and Delampady, M. (1987) Testing Precise Hypotheses. Statistical Science, 2, 317-335.
[17] Meng, X.-L. (1994) Posterior Predictive p-Values. The Annals of Statistics, 22, 1142-1160.
[18] Yin, Y. and Zhao, J. (2013) Testing Normal Means: The Reconcilability of the p Value and the Bayesian Evidence. The Scienti_c World Journal, 2013, Article ID: 381539.
[19] Pestman, W., Tuerlinckx, F. and Vanpaemel, W. (2018) A Reverse to the Je_reys-Lindley Paradox. Probability and Mathematical Statistics, 38, 243-247.

comments powered by Disqus

Copyright © 2020 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.