Author： Wang Zijun
Publisher： Taylor & Francis Ltd
ISSN： 0361-0926
Source： Communications in Statistics: Theory and Methods, Vol.38, Iss.14, 2009-01, pp. : 2302-2320
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
Nonparametric model specification for stationary time series involves selections of the smoothing parameter (bandwidth), the lag structure and the functional form (linear vs. nonlinear). In real life problems, none of these factors are known and the choices are interdependent. In this article, we recommend to accomplish these choices in one step via the model selection approach. Two procedures are considered; one based on the information criterion and the other based on the least squares cross validation. The Monte Carlo simulation results show that both procedures have good finite sample performances and are easy to implement compared to existing two-step probabilistic testing procedures.
Related content
Access to resources
Recommend
Nonparametric approach to intervention time series modeling
Journal of Applied Statistics, Vol. 39, Iss. 7, 2012-07 ,pp. :