The empirical likelihood method of Owen (1988) is a nonparametric method of inference. The method gains an advantage over the classical or the modern. The semiparametric regress model is important model developed in 1980's. It colligates the merits of regress model and nonparametric model. Therefore it has strong application property.In this paper, we consider the application of the empirical likelihood method to semiparametric model:wherexi = (xi1,xi2,…,xik)'is non-random design variable, β = (β1,β2,…,βk)'is the unknown parameter, g(·)is the unknown real-valued function on Rk, ei is therandom error variable with Eei =0, Eei2 =σ2 <∞, a nonparametric version of theWilks theorem is derived. The result is used to construct the confidence region of parameter vector. Consider the application of the empirical likelihood method to the Errors-In-Variables semiparametric Regress Model:Where Xi is the k-dimensional vector can't be observed, xi is the k-dimensional vector can be observed, δi is the random error variable with Eδi, = 0,. We prove that the empirical log-likelihood isasymptotic chi-square distribution. |