Kullback-Leibler life time testing

The paper deals with testing the hypotheses for homogeneity and point null value of the scale parameter in the gamma family. Tests suggested here are based upon the Kullback–Leibler divergence from an observed vector to the canonical parameter (see Pazman, 1993 [14]), and upon its decomposition. The latter is used to derive the exact distribution of the test statistic by convolution. A geometric integration method is used alternatively to derive the distribution directly. Because it is observed by simulation, that the test’s performance is poor when the shape parameter is estimated from the data, an interval method is developed and its use is demonstrated in an analysis of real data.

[1]  M. Stehlík,et al.  I-divergence based testing with applications to reliability and physics , 2012 .

[2]  Andrej Pázman,et al.  Nonlinear Statistical Models , 1993 .

[3]  A. Karagrigoriou,et al.  On Distributional Properties and Goodness-of-Fit Tests for Generalized Measures of Divergence , 2010 .

[4]  J. F. C. Kingman,et al.  Information and Exponential Families in Statistical Theory , 1980 .

[5]  Milan Stehlík,et al.  Decompositions of information divergences: Recent development, open problems and applications , 2012 .

[6]  Gaston H. Gonnet,et al.  On the LambertW function , 1996, Adv. Comput. Math..

[7]  C. Hennig,et al.  How to find an appropriate clustering for mixed‐type variables with application to socio‐economic stratification , 2013 .

[8]  W. Richter.  Exact distributions under non-standard model assumptions , 2012 .

[9]  Frantisek Rublík.  On optimality of the LR tests in the sense of exact slopes. I. General case , 1989, Kybernetika.

[10]  W. Richter,et al.  Geometric Generalization of the Exponential Law , 2002 .

[11]  P. Royston,et al.  Regression using fractional polynomials of continuous covariates: parsimonious parametric modelling. , 1994 .

[12]  M. Stehlík.  Distributions of exact tests in the exponential family , 2003 .

[13]  Milan Stehlík,et al.  On Small Samples Testing for Frailty Through Homogeneity Test , 2015, Commun. Stat. Simul. Comput..

[14]  Kwun Chuen Gary Chan,et al.  Nuisance parameter elimination for proportional likelihood ratio models with nonignorable missingness and random truncation. , 2013, Biometrika.

[15]  Milan Stehlík,et al.  Homogeneity and scale testing of generalized gamma distribution , 2008, Reliab. Eng. Syst. Saf..

[16]  W. Richter.  Ellipses numbers and geometric measure representations , 2011 .

[17]  D. Coit,et al.  Gamma distribution parameter estimation for field reliability data with missing failure times , 2000 .

[18]  Frantisek Rublík.  On optimality of the LR tests in the sense of exact slopes. II. Application to individual distributions , 1989, Kybernetika.

[19]  W. Richter.  Continuous ln,p-symmetric distributions , 2009 .

[20]  P. Royston,et al.  Building multivariable prognostic and diagnostic models: transformation of the predictors by using fractional polynomials , 1999 .

[21]  Jerald F. Lawless,et al.  Statistical Models and Methods for Lifetime Data. , 1983 .

[22]  A. Kimber.  Trimming in Gamma Samples , 1983 .

[23]  Z. Q. Lu.  Statistical Inference Based on Divergence Measures , 2007 .

[24]  D. Kendall,et al.  The Statistical Analysis of Variance‐Heterogeneity and the Logarithmic Transformation , 1946 .