Title :
The minimum discrepancy measure: its use in univariate white noise tests
Author :
Chen, Rong-Ming ; Chang, Shyang
Author_Institution :
Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
fDate :
2/1/1993 12:00:00 AM
Abstract :
A white noise test based on a minimum discrepancy measure (MDM) is proposed. The corresponding MDM testing rule is consistent in the sense that it will determine the correct statistics of the observed time series as the number of data samples tends to infinity. Simulation results are given to illustrate the effectiveness of the testing algorithm
Keywords :
information theory; signal processing; statistical analysis; time series; white noise; ARMA process; MDM testing rule; minimum discrepancy measure; statistics; time series; univariate white noise tests; Autocorrelation; Delay; H infinity control; Noise measurement; Nonlinear filters; Polynomials; Signal processing algorithms; Statistical analysis; Testing; White noise;
Journal_Title :
Signal Processing, IEEE Transactions on