论文信息 - Testing and estimating for change in long memory parameter

Testing and estimating for change in long memory parameter

We consider a long memory time series where the long-memory parameter H appears to change with time. We are interested in detecting and estimating the change-point and studying the asymptotic properties of the estimator and the test statistic. We apply the method to two practical data series to investigate the presence of change in H. Simulations and data examples confirm the validity of the test and estimation.

Jinde Wang | Lihong Wang

[1] J. Beran. A Goodness‐Of‐Fit Test for Time Series with Long Range Dependence , 1992 .

[2] P. Robinson. Semiparametric Analysis of Long-Memory Time Series , 1994 .

[3] B. Ray,et al. Bayesian methods for change‐point detection in long‐range dependent processes , 2002 .

[4] Lajos Horváth,et al. LIMIT THEOREMS FOR QUADRATIC FORMS WITH APPLICATIONS TO WHITTLE'S ESTIMATE , 1999 .

[5] Tailen Hsing,et al. Limit theorems for functionals of moving averages , 1997 .

[6] Lajos Horváth,et al. Change-Point Detection in Long-Memory Processes , 2001 .

[7] M. Taqqu,et al. Noncentral Limit Theorems for Quadratic Forms in Random Variables Having Long-Range Dependence , 1985 .

[8] Jan Beran,et al. Statistics for long-memory processes , 1994 .

[9] J. Geweke,et al. THE ESTIMATION AND APPLICATION OF LONG MEMORY TIME SERIES MODELS , 1983 .

[10] Jan Beran,et al. Testing for a change of the long-memory parameter , 1996 .

[11] P. Révész,et al. Strong approximations in probability and statistics , 1981 .