z-logo
Premium
Empirical Likelihood for Non‐Smooth Criterion Functions
Author(s) -
MOLANES LOPEZ ELISA M.,
KEILEGOM INGRID VAN,
VERAVERBEKE NOËL
Publication year - 2009
Publication title -
scandinavian journal of statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.359
H-Index - 65
eISSN - 1467-9469
pISSN - 0303-6898
DOI - 10.1111/j.1467-9469.2009.00640.x
Subject(s) - mathematics , nuisance parameter , quantile , independent and identically distributed random variables , likelihood ratio test , multivariate random variable , empirical likelihood , limit (mathematics) , score test , function (biology) , limit of a function , sequence (biology) , statistics , likelihood function , inference , combinatorics , random variable , maximum likelihood , mathematical analysis , estimator , artificial intelligence , genetics , evolutionary biology , biology , computer science
.  Suppose that X 1 ,…,  X n is a sequence of independent random vectors, identically distributed as a d ‐dimensional random vector X . Let be a parameter of interest and be some nuisance parameter. The unknown, true parameters ( μ 0 , ν 0 ) are uniquely determined by the system of equations E { g ( X , μ 0 , ν 0 )} =   0 , where g  =  ( g 1 ,…, g p + q ) is a vector of p + q functions. In this paper we develop an empirical likelihood (EL) method to do inference for the parameter μ 0 . The results in this paper are valid under very mild conditions on the vector of criterion functions g . In particular, we do not require that g 1 ,…, g p + q are smooth in μ or ν . This offers the advantage that the criterion function may involve indicators, which are encountered when considering, e.g. differences of quantiles, copulas, ROC curves, to mention just a few examples. We prove the asymptotic limit of the empirical log‐likelihood ratio, and carry out a small simulation study to test the performance of the proposed EL method for small samples.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here