An estimation method for the Neyman chi-square divergence with application to test of hypotheses

We propose a new definition of the Neyman chi-square divergence between distributions. Based on convexity properties and duality, this version of the χ2 is well suited both for the classical applications of the χ2 for the analysis of contingency tables and for the statistical tests in parametric models, for which it is advocated to be robust against outliers.We present two applications in testing. In the first one, we deal with goodness-of-fit tests for finite and infinite numbers of linear constraints; in the second one, we apply χ2-methodology to parametric testing against contamination.

[1]  B. Lindsay.  Efficiency versus robustness : the case for minimum Hellinger distance and related methods , 1994 .

[2]  I. Vajda,et al.  Asymptotic divergence of estimates of discrete distributions , 1995 .

[3]  D. Pollard.  Convergence of stochastic processes , 1984 .

[4]  Pascal Massart,et al.  STRONG APPROXIMATION FOR MULTIVARIATE EMPIRICAL AND RELATED PROCESSES, VIA KMT CONSTRUCTIONS , 1989 .

[5]  H. O. Lancaster.  The chi-squared distribution , 1971 .

[6]  Timothy R. C. Read,et al.  Multinomial goodness-of-fit tests , 1984 .

[7]  P. Bickel,et al.  Efficient estimation of linear functionals of a probability measure P with known marginal distributions , 1991 .

[8]  Piet Groeneboom,et al.  Large Deviation Theorems for Empirical Probability Measures , 1979 .

[9]  I. Vajda,et al.  Some New Statistics for Testing Hypotheses in Parametric Models , 1997 .

[10]  Vladimir Koltchinskii,et al.  Komlos-Major-Tusnady approximation for the general empirical process and Haar expansions of classes of functions , 1994 .

[11]  J. Wellner,et al.  Empirical Processes with Applications to Statistics , 2009 .

[12]  A. F. Smith,et al.  Statistical analysis of finite mixture distributions , 1986 .

[13]  N. Bingham.  EMPIRICAL PROCESSES WITH APPLICATIONS TO STATISTICS (Wiley Series in Probability and Mathematical Statistics) , 1987 .

[14]  Guido W. Imbens,et al.  Empirical likelihood estimation and consistent tests with conditional moment restrictions , 2003 .

[15]  Marc Teboulle,et al.  Convergence of best phi-entropy estimates , 1993, IEEE Trans. Inf. Theory.

[16]  A. Owen.  Empirical Likelihood Ratio Confidence Regions , 1990 .

[17]  M. Broniatowski,et al.  Minimization of divergences on sets of signed measures , 2010, 1003.5457.

[18]  I. Vajda,et al.  Convex Statistical Distances , 2018, Statistical Inference for Engineers and Data Scientists.

[19]  T. Ledwina,et al.  Asymptotic behavior of some bilinear functionals of the empirical process , 1992 .

[20]  S. R. Searle.  Linear Models , 1971 .

[21]  Y. Shao,et al.  On robustness and efficiency of minimum divergence estimators , 2001 .

[22]  Whitney K. Newey,et al.  Higher Order Properties of Gmm and Generalized Empirical Likelihood Estimators , 2003 .

[23]  M. Broniatowski,et al.  ESTIMATION AND TESTS FOR MODELS SATISFYING LINEAR CONSTRAINTS WITH UNKNOWN PARAMETER , 2008, 0811.3477.

[24]  Mohamed Lemdani,et al.  Likelihood ratio tests in contamination models , 1999 .

[25]  P. Massart,et al.  HUNGARIAN CONSTRUCTIONS FROM THE NONASYMPTOTIC VIEWPOINT , 1989 .

[26]  R. Beran.  Minimum Hellinger distance estimates for parametric models , 1977 .