本文检验部分线性回归模型(PLM)中,误差的方差未知时,函数部分是否是线性函数,在备择假设下,先用局部多项式方法估计出函数部分,再估计参数部分。计算出了零假设下广义似然比(GLR)检验统计量的表达式,给出了它的渐近分布,并对结果进行了模拟。
We propose the test statistic to check whether the nonparametric function in partially linear models (PLM) is linear or not when variance of error is unknown. We estimate the nonparametric function by using local polynomial method, and estimate the parameters by the least square method. The generalized likelihood ratio (GLR) test statistic under the null hypothesis is derived, and it is shown to be asymptotically normal.