A simple additivity test for conditionally heteroscedastic nonlinear autoregression

详细信息	查看全文 | 推荐本文 |

• 作者：Michael Levine ; ^{mlevins@purdue.edu} ; ^{mlevins@stat.purdue.edu} ; Jinguang (Tony) Li
• 关键词：Nonlinear autoregressive model ; Additivity test ; Heteroscedasticity ; Unbalanced ANOVA with unequal variances
• 刊名：Computational Statistics and Data Analysis
• 出版年：2012
• 期刊代码：19_01679473
• 类别：cp
• 出版时间：August, 2012
• 卷：56
• 期：8
• 页码：2421-2429
• 文件大小：245 K

摘要

In this article, we propose a test for the additivity of a nonlinear conditionally heteroscedastic autoregressive model. The test is based on the unequal variance unbalanced design ANOVA scheme. An asymptotic distribution of the test statistic is derived and the test performance in finite samples is studied using simulation. To the best of our knowledge, this is the first additivity test for a conditionally heteroscedastic time series model.