CONSISTENT AND ASYMPTOTICALLY NORMAL ESTIMATORS FOR PERIODIC BILINEAR MODELS

다국어 초록 (Multilingual Abstract)

In this paper, a distribution free approach to the parameter estimation of a simple bilinear model with periodic coefficients is presented. The proposed method relies on minimum distance estimator based on the autocovariances of the squared process. Consistency and asymptotic normality of the estimator, as well as hypotheses testing, are derived. Numerical experiments on simulated data sets are presented to highlight the theoretical results.

참고문헌 (Reference)

1 A. Bibi, "Yule-Walker type estimators in periodic bilinear models: strong consistency and asymptotic normality" 19 : 1-30, 2010

2 A. Bibi, "Propriétés dans L2 et estimation des processus purement bilineaires et strictement superdiagonaux à coefficients périodiques" 34 (34): 131-148, 2006

3 A. Bibi, "On the covariance structure of time varying bilinear models" 21 (21): 25-60, 2003

4 W. K. Newey, "Large sample estimation and hypothesis testing. in: Handbook of econometrics, Vol. IV" North-Holland 2111-2245, 1994

5 P. J. Brockwell, "Introduction to Time Series and Forecasting" Springer-Verlag 1996

6 A. Hall, "Generalized Method of Moments" Oxford University Press 2005

7 A. Bibi, "Estimation of some bilinear time series models with time varying coefficients" 22 (22): 355-376, 2004

8 A. Gautier, "Asymptotic inefficiency of mean-correction on parameter estimation for a periodic first-order autoregressive model" 35 (35): 2083-2106, 2006

9 C. Francq, "ARMA models with bilinear innovations" 15 (15): 29-52, 1999