一个新的稳健 ARCH 检验和 YJ-GARCH 模型.PDFVIP

该文已经被《统计研究》接受，即将发表。 一个新的稳健ARCH 检验和YJ-GARCH 模型 李海奇 Sung Y. Park 摘要：众所周知，Engle (1982) 的 ARCH 检验对于条件均值模型误设并不稳健，特别地， 当条件均值是非线性过程而我们仅对之建立线性模型时，它过度地拒绝真实的原假设，导 致出现严重的水平扭曲 (size distortion) 。因此，本文在文献当中首次利用Yeo-Johnson 变换 方法来转换均值模型的因变量以排除ARCH 过程中均值部分的非线性，进而提出一个新的 稳健ARCH 检验以及一个新的GARCH 模型——Yeo-Johnson (YJ) GARCH 模型。蒙特卡罗 模拟结果表明，稳健的ARCH 检验在水平 (size) 和势 (power) 方面的表现要显著优于Engle (1982) 的ARCH 检验。对上证综指收益率的实证研究结果表明，YJ-GARCH 模型的拟合效 果要显著优于线性GARCH 模型。 关键词：稳健ARCH 检验 Yeo-Johnson 变换 YJ-GARCH 模型 水平扭曲 中图分类号：O212 文献标识码：A A New Robust ARCH Test and YJ-GARCH Model Haiqi Li and Sung Y. Park Abstract: It is quite well known that Engle (1982)’s ARCH test is not robust to misspecification of the conditional mean model. Especially, when the conditional mean is nonlinear process and we model it by a linear model, it rejects the true null hypothesis too often and thus causes the serious size distortion. This paper proposes a new robust ARCH test using the Yeo-Johnson transformation in which the dependent variable is transformed to deal with nonlinearity. This alternative model specification yields a new GARCH model, i.e. Yeo-Johnson (YJ) GARCH by product. The Monte Carlo simulation results show that the robust ARCH test is significantly superior to Engle (1982)’s ARCH test in terms of the size and power. Empirical application to the returns of Shanghai Composite index illustrates that the goodness-of-fit for YJ-GARCH model is clearly better than the linear GARCH model. Keywords: Robust ARCH Test, Yeo-Johnson Transformation, YJ-GARCH Model, Size Distortion 1 一、引言 自从Engle (1982)[1] 和Bollerslev (1986)[2] 分别提出ARCH ( Autoregressive Conditional Heteroskedasticity, 自回归条件异方差) 模型和GARCH (Generalized