预测回归模型序列相关性的Jackknife经验似然比检验

A Jackknife Empirical Likelihood Ratio Test for Serial Correlation of Predictive Regression Model

预测回归模型是计量经济学中的重要模型,而相关的序列检验问题在文献中尚未被提及.考虑到序列相关性检验在模型实证中的重要性,文章基于Jackknife经验似然法,构造了该模型的序列相关检验统计量,并在一定条件下推导了零假设成立时检验统计量的渐近分布,分析了它在局部备择假设下的功效情况,最后通过随机模拟和实际数据例子验证了该检验方法的有限样本性质.

Predictive regression model is a very important model in econometrics.However,the issue of its serial correlation test has not been mentioned in the literature.Considering the importance of the serial correlation test in the empirical study,this paper considers a jackknife empirical likelihood based serial correlation test.The limit distribution,as well as the power property at local alterative hypotheses,of this statistic has been derived under certain conditions.A few examples are also given to illustrate its finite sample performance in terms of size and power based on some simulated and real data sets.