Testing for changes in polynomial regression

Testing for changes in polynomial regression
复制标题

DOI:
10.3150/08-bej122
复制
发表时间:
2008-08
期刊:
影响因子:
1.5
通讯作者:
Alexander Aue;Lajos Horv'ath;Marie Huvskov'a;P. Kokoszka
Alexander Aue;Lajos Horv'ath;Marie Huvskov'a;P. Kokoszka
中科院分区:
数学2区
文献类型:
--
作者:
Alexander Aue;Lajos Horv'ath;Marie Huvskov'a;P. Kokoszka

文献摘要

被引文献

相似文献

我们考虑一个非线性多项式回归模型,在这个模型中,我们希望检验回归参数的结构稳定性的零假设,而不是在一个未知的时间发生突变。本文给出了与最大似然比渐近等价的极大型检验统计量的极值分布。由此产生的测试易于应用,即使在小样本中也具有良好的尺寸和功率。
We consider a nonlinear polynomial regression model in which we wish to test the null hypothesis of structural stability in the regression parameters against the alternative of a break at an unknown time. We derive the extreme value distribution of a maximum-type test statistic which is asymptotically equivalent to the maximally selected likelihood ratio. The resulting test is easy to apply and has good size and power, even in small samples.