作者: Marcelo Fernandes , Pierre-Yves Preumont
DOI: 10.12660/BRE.V32N22012.18608
关键词:
摘要: This paper uses a multivariate response surface methodology to analyze the size distortion of BDS test when applied standardized residuals rst-order GARCH processes. The results show that asymptotic standard normal distribution is an unreliable approximation, even in large samples. On other hand, simple log-transformation squared seems correct most problems. Nonetheless, estimated surfaces can provide not only measure distortion, but also more adequate critical values for small