Identification of Nonlinear Times Series from First Order Cumulative Characteristics.
Abstract
We consider the problem of identifying the class of time series model to which a series belongs based on observation of part of the series. Techniques of nonparametric estimation have been applied to this problem by various authors using kernel estimates of the one-step lagged conditional mean and variance functions. We study cumulative versions of Tukey regressogram estimators of such functions. These are more stable than estimates of the mean and variance functions themselves and can be used to construct confidence bands. Goodness of fit tests for specific parametric models are also developed.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1991
- Accession Number
- ADA239822
Entities
People
- Ian W. Mckeague
- Mei-jie Zhang
Organizations
- Florida State University