Time Series Models and Mathematica
This notebook introduces a package of Mathematica functions that manipulate autoregressive, integrated moving average (ARIMA) models. ARIMA models describe discrete-time stochastic processes—time series. The models are most adept at modeling stationary processes. Through differencing, however, these models accommodate certain forms of nonstationary processes as well.
KeywordsTransfer Function Spectral Density Unit Circle Time Series Model ARMA Model
Unable to display preview. Download preview PDF.
- Bloomfield, P. (1976). Introduction to Spectral Analysis. New York. Wiley.Google Scholar
- Cabrara, J. F. and A. R. Wilks (1992). “An interface from S to Mathematica”. The Mathematica Journal, 2, 66–74.Google Scholar
- Evans, B. L., J. H. McClelland, and W. B. McClure (1990). “Symbolic transforms with applications to signmal processing.” The Mathematica Journal 1, 70–80.Google Scholar
- Stine, R. A. (1990). “Mathematica in time series analysis.” Proceedings of the Statistical Computing Section of the American Statistical Association. Washington DC 37–45Google Scholar
- Wolfram, S. (1991). Mathematica: A System for Doing Mathematics by Computer. Redwood City, Addison-Wesley.Google Scholar