Title :
Minimum message length moving average time series data mining
Author :
Sak, Mony ; Dowe, David L. ; Ray, Sid
Author_Institution :
Clayton Sch. of Inf. Technol., Monash Univ., Clayton, Vic.
Abstract :
This paper considers a criterion for selection of moving average (MA) time series models based upon the information-theoretic principle of minimum message length (MML). We derive an MML model selection criterion for invertible MA time series models using the Wallace and Freeman (1987) MML approximation, MML87. The MML model order selection performance is compared with other well-known model selection criteria such as Akaike´s information criterion (AIC), corrected AIC (AICc), Bayesian information criterion (BIC), minimum description length (MDL, 1978), and the Hannan-Quinn (HQ) criterion. Our experiments show that the MML-based criterion achieves the lowest average mean squared prediction error and the best average log likelihood, and has the best ability to choose the true MA model order for smaller sample sizes
Keywords :
data mining; forecasting theory; information theory; time series; Akaike information criterion; Bayesian information criterion; Hannan-Quinn criterion; average log likelihood; average mean squared prediction error; information-theoretic principle; machine learning; minimum description length; minimum message length approximation; moving average time series data mining; time series analysis; time series forecasting; Australia; Autoregressive processes; Data mining; Decision trees; Econometrics; Information technology; Phylogeny; Polynomials; Predictive models; Yttrium; Data mining; Machine learning; Time series analysis and forecasting;
Conference_Titel :
Computational Intelligence Methods and Applications, 2005 ICSC Congress on
Conference_Location :
Istanbul
Print_ISBN :
1-4244-0020-1
DOI :
10.1109/CIMA.2005.1662352
