ESTAR-GARCH模型的单位根检验

The Unit Root Test of ESTAR-GARCH Model

ESTAR-GARCH模型的单位根检验所选取的统计量通常需要估计方差,因此本文提出了经验似然比统计量,避免了方差计算带来的误差,并推导出了该统计量的极限分布.通过模拟其临界值,对比研究了经验似然比统计量和基于QML法的KSS型检验统计量t(δ)的检验功效.Monte Carlo模拟证实,本文提出的经验似然比统计量比检验统计量t(δ)具有更好的检验水平和更高的检验功效.因此本文提出的统计量通过避免方差的计算而提高了检验的准确性.最后,通过上证指数的实证分析,进一步说明了该统计量具有良好的检验功效.

The existing statistics in unit root tests of ESTAR-GARCH model often need to calculate the variance of specimen.In this paper,the empirical likelihood ratio statistics are proposed to deduce the limiting distribution of them,so that the random errors caused by variance calculation are avoided.And then,a critical value of the statistics can be received through simulation,the power of the QML test and the empirical likelihood ratio statistics has been compared and studied.Monte Carlo simulation shows that compared with the QML test,the power and the criterion of tests is more fruitful and more scientific,through the empirical likelihood ratio statistics.Avoiding the random errors of the calculation of variance,the accuracy of tests is clearly increased by using the empirical likelihood ratio statistics.Finally,the empirical study of SSE can further illustrate the higher test efficiency of this statistic.