Comparison of automated procedures for ARMA model identification
Tóm tắt
This article evaluates the performance of three automated procedures for ARMA model identification commonly available in current versions of SAS for Windows: MINIC, SCAN, and ESACF. Monte Carlo experiments with different model structures, parameter values, and sample sizes were used to compare the methods. On average, the procedures either correctly identified the simulated structures or selected parsimonious nearly equivalent mathematical representations in at least 60% of the trials conducted. For autoregressive models, MINIC achieved the best results. SCAN was superior to the other two procedures for mixed structures. For moving-average processes, ESACF obtained the most correct selections. For all three methods, model identification was less accurate for low dependency than for medium or high dependency processes. The effect of sample size was more pronounced for MINIC than for SCAN and ESACF. SCAN and ESACF tended to select higher-order mixed structures in larger samples. These findings are confined to stationary nonseasonal time series.
Tài liệu tham khảo
Akaike, H. (1974). A new look at the statistical model identification. IEEE Transactions on Automatic Control, 19, 716–723.
Algina, J., & Swaminathan, H. A. (1977). A procedure for the analysis of time series designs. Journal of Experimental Education, 45, 56–60.
Algina, J., & Swaminathan, H. A. (1979). Alternatives to Simonton’s analysis of interrupted and multiple-group time series designs. Psychological Bulletin, 86, 919–926.
Beguin, J. M., Gourieroux, C., & Montfort, A. (1980). Identification of mixed autoregressive-moving average process: The corner method. In O. D. Anderson & M. R. Perryman (Eds.), Time series analysis: Proceedings of the international conference held at Houston, Texas, August 1980 (pp. 423–436). Amsterdam: North-Holland.
Bowerman, B. L., & O’Connell, R. T. (1993). Forecasting and time series: An applied approach. Belmont: Duxbury Press.
Box, G. E. P., & Jenkins, G. M. (1970). Time series analysis: Forecasting and control. San Francisco: Holden-Day.
Box, G. E. P., Jenkins, G. M., & Reinsel, G. C. (1994). Time series analysis: Forecasting and control (3rd ed.). Englewood Cliffs, NJ: Prentice Hall.
Box, G. E. P., & Pierce, W. A. (1970). Distribution of residual autocorrelations in autoregressive-integrated moving average time series models. Journal of American Statistical Association, 65, 1509–1526.
Brockwell, P. J., & Davis, R. A. (2002). Introduction to time series and forecasting (2nd ed.). New York: Springer.
Chan, W.-S. (1999). A comparison of some of pattern identification methods for order determination of mixed ARMA models. Statistics & Probability Letters, 42, 69–79.
Choi, B. S. (1992). ARMA model identification. New York: Springer.
Crosbie, J. (1993). Interrupted time-series analysis with brief single-subject data. Journal of Consulting & Clinical Psychology, 61, 966–974.
Delcor, L., Cadopi, M., Delignieres, D., & Mesure, S. (2002). Dynamics of the memorization of a morphokinetic movement sequence. Neuroscience Letters, 336, 25–28.
Dickey, D. A. (2004). Applied time series notes (Notes). Available at www.stat.ncsu.edu/people/dickey/st730/Notes/p._38_55.pdf.
Djuric, P. M., & Kay, S. M. (1992). Order Selection of autoregressive models. IEEE Transactions on Acoustics, Speech, & Signal Processing, 40, 2829–2833.
Fortes, M., Ninot, G., & Delignières, D. (2005). The auto-regressive integrated moving average procedures implications for adapted physical activity research. Adapted Physical Activity Quarterly, 22, 221–236.
Fraschini E. M., & Axausten, K. W. (2001). Day on day dependencies in travel: First results using ARIMA modeling (Working paper). Available at e-collection.ethbib.ch.
Gilden, D. L. (2001). Cognitive emissions of 1/ƒ noise. Psychological Review, 108, 33–56.
Glass, G. V., Willson, V. L., & Gottman, J. M. (1975). Design and analysis of time-series experiments. Boulder, CO: Colorado Associated University Press.
Gottman, J. M. (1981). Time-series analysis. Cambridge: Cambridge University Press.
Granger, C. W. J., & Newbold, P. (1986). Forecasting economic time series. San Diego: Academic Press.
Hannan, E. J., & Rissanen, J. (1982). Recursive estimation of mixed autoregressive moving average order. Biometrika, 69, 81–94.
Harrop, J. W., & Velicer, W. F. (1985). A comparison of three alternative methods of time series model identification. Multivariate Behavioral Research, 20, 27–44.
Harrop, J. W., & Velicer, W. F. (1990). Computer programs for interrupted time series analysis: II. A quantitative evaluation. Multivariate Behavioral Research, 25, 233–248.
Huitema, B. E. (2002). Time-series intervention analysis using ITSA-CORR: Fatal flaws. Manuscript submitted for publication.
Huitema, B. E. (2004). Analysis of interrupted time-series experiments using ITSE: A critique. Understanding Statistics, 3, 27–46.
Koreisha, S. G., & Pukkila, T. M. (1990). A generalized least-squares approach for estimation of autoregressive moving-average models. Journal of Time Series Analysis, 11, 139–151.
Koreisha, S. G., & Yoshimoto, G. (1991). A comparison among identification procedures for autoregressive moving average models. International Statistical Review, 59, 37–57.
Dung, G. M., & Box, G. E. P. (1978). On a measure of lack of fit in time series models. Biometrika, 65, 297–303.
Makridakis, S., Wheelwright, S. C., & Hyndman, R. J. (1998). Forecasting: Methods and applications. New York: Wiley.
Marks-Tarlow, T. (1999). The self as a dynamical system. Nonlinear Dynamics, Psychology & Life Sciences, 3, 311–345.
Marsh, J. C., & Shibano, M. (1984). Issues in the statistical analysis of clinical time-series data. Social Work Research & Abstracts, 20, 7–12.
McCleary, R., & Hay, R. A., Jr. (1980). Applied time series analysis for the social sciences. Beverly Hills, CA: Sage.
McKnight, S., McKean, J. W., & Huitema, B. E. (2000). A double bootstrap method to analyze linear models with autoregressive error terms. Psychological Methods, 5, 87–101.
Ninot, G., Fortes, M., & Delignières, D. (2005). The dynamics of self-esteem in adults over a six-month period: An exploratory study. Journal of Psychology, 139, 315–330.
Pukkila, T. M., Koreisha, S., & Kallinen, A. (1990). The identification of ARMA models. Biometrika, 77, 537–548.
Rankin, E. D., & Marsh, J. C. (1985). Effects of missing data on the statistical analysis of clinical time series. Social Work Research & Abstracts, 21, 13–16.
Revenstorf, D., Kessler, A., Schindler, L., Hahlweg, K., & Bluemner, E. (1980). Time series analysis: Clinical applications evaluating intervention effects in diaries. In O. D. Anderson (Ed.), Analysing time series: Proceedings of the international conference held on Guernsey, Channel Islands, October 1979 (pp. 291–312). Amsterdam: North-Holland.
Rissannen, J. (1978). Modeling the shortest data description. Automatica, 14, 465–471.
Rosel, J., & Elósegui, E. (1994). Daily an weekly smoking habits: A Box Jenkins analysis. Psychological Reports, 75, 1639–1648.
SAS Institute (1999). SAS/ETS (Version 8) [Software]. Cary, NC: Author.
Schwarz, G. (1978). Estimation the dimension of a model. Annals of Statistics, 6, 461–469.
Simonton, D. K. (1977). Cross-sectional time-series experiments. Some suggested statistical analysis. Psychological Bulletin, 84, 489–502.
Stadnytska, T., Braun, S., & Werner, J. (2007). Model identification of integrated ARMA processes. Manuscript submitted for publication.
Thornton, T. L., & Gilden, D. L. (2005). Provenance of correlation in psychological data. Psychonomic Bulletin & Review, 12, 409–441.
Tsay, R. S., & Tiao, G. C. (1984). Consistent estimates of autoregressive parameters and extended sample autocorrelation function for stationary and nonstationary ARMA models. Journal of American Statistical Association, 79, 84–96.
Tsay, R. S., & Tiao, G. C. (1985). Use of canonical analysis in time series model identification. Biometrika, 72, 299–315.
Tsay, R. S., & Tiao, G. C. (1990). Asymptotic properties of multivariate nonstationary processes with applications to autoregressions. Annals of Statistics, 18, 220–250.
Velicer, W. F., & Colby, S. M. (1997). Tune series analysis for prevention and treatment research. In K. J. Bryant, M. Windle, & S. G. West (Eds.), The science of prevention: Methodological advances from alcohol and substance abuse research (pp. 211–249). Washington, DC: American Psychological Association.
Velicer, W. F., & Fava, J. l. (2003). Time series analysis. In J. Schinka & W. F. Velicer (Eds.), Research methods in psychology (pp. 581–606). New York: Wiley.
Velicer, W. F., & Harrop, J. W. (1983). The reliability and accuracy of time series model identification. Evaluation Review, 7, 551–560.
Velicer, W. F., & McDonald, R. P. (1984). Time series analysis without model identification. Multivariate Behavioral Research, 19, 33–47.
Velicer, W. F., & McDonald, R. P. (1991). Cross-sectional time series design: A general transformation approach. Multivariate Behavioral Research, 26, 247–254.
Velicer, W. F., Redding, C. A., Richmond, R., Greeley, J., & Swift, W. (1992). A time series investigation of tree nicotine regulation models. Addictive Behaviors, 17, 325–345.
Velicer, W. F., Rossi, J. S., Diclemente, C. C., & Prochaska, J. O. (1996). A criterion measurement model for health behavior change. Addictive Behaviors, 21, 555–584.
Wagenmakers, E.-J., Farrell, S., & Ratcliff, R. (2004). Estimation an interpretation of 1/ƒα noise in human cognition. Psychonomic Bulletin & Review, 11, 579–615.
Williams, E. A., & Gottman, J. M. (1999). A user’s guide to the Gottmann-Williams time-series analysis computer programs for social scientists. Cambridge: Cambridge University Press.