Title :
Order identification of ARMA models based on instrumental variable estimators
Author_Institution :
Dept. of Econ. & Bus., North Carolina State Univ., Raleigh, NC, USA
fDate :
9/1/1991 12:00:00 AM
Abstract :
The author proposes a simple model selection procedure based on IV estimators, which can be viewed as an extension of P. Stoica´s method (1981). The model selection procedure is based on a simple statistic with a known limiting distribution. It closely parallels the overfitting strategy applied to models estimated by nonlinear least squares
Keywords :
parameter estimation; statistical analysis; time series; ARMA models; instrumental variable estimators; model selection; nonlinear least squares; overfitting strategy; parameter estimation; statistical analysis; time series; Autocorrelation; Autoregressive processes; Equations; Inspection; Instruments; Least squares approximation; Parameter estimation; Statistical distributions; Testing; Time series analysis;
Journal_Title :
Automatic Control, IEEE Transactions on
