Upper Bound of the Generalize p-Value for the Behrens-Fisher Problem with a Known Ratio of Variances

Authors: Rada Somkhuean, Suparat Niwitpong, Sa-aat Niwitpong

Abstract:

This paper presents the generalized p-values for testing the Behrens-Fisher problem when a ratio of variance is known. We also derive a closed form expression of the upper bound of the proposed generalized p-value.

Keywords: Generalized p-value, hypothesis testing, ratio of variances, upper bound.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1087826

References:

[1] E. Schechtman, and M. Sherman, “The two-sample t-test with a known ratio of Variances”, Statistical Methodology, Vol.4, pp. 508-514, 2007.
[2] F.E. Satterthwaite, “An approximate distribution of estimates of variance components”, Biometric Bulletin, Vol.6, pp. 110-114, 1946.
[3] S. Niwitpong, and Sa. Niwitpong, “Confidence interval for the difference of two normal population means with a known ratio of variances”, Applied Mathematical Sciences, Vol.4, pp. 347359, 2010.
[4] B.L. Welch, “The significance of the difference between two means when the population variances are unequal”, Biometrika, Vol.29, pp. 350-362, 1983.
[5] S. Weerahandi, “Exact Statistical Methods for Data Analysis”, Springer, NewYork, 1995.
[6] K-W. Tsui, and S. Weerahandi, “Generalized p-values in significance testing of hypotheses in the presence of nuisance parameters”, J. Amer Statist Assoc, Vol.84, pp. 60207, 1989.
[7] S. Tang,and K-W. Tsui, “Distributional properties for the generalized p-value for the BehrensFisher problem”, Statistics Probability Letters, Vol.77, pp. 18, 2007.