Stat 6540 Time series

Description

The course consists of a survey of the theory and methods of time series analysis. The goal is to present modern techniques for handling data and at the same time to provide a thorough understanding of the mathematical basis for the techniques. Both time and frequency domain methods are discussed, but emphasis is placed on time domain. Topics cover stationary univariate and multivariate time series, ARMA, ARIMA, model building and forecasting as well as state-space models.

Prerequisites

A solid backround in linear algebra and regression methods, a graduate course in statistical inference.

References

  • Time series: theory and methods, 2nd ed. by Peter J. Brockwell and  Richard A. Davis. Springer Series in Statistics, 2009.
  • Fourier analysis of time series: an introduction, 2nd ed. by Peter Bloomfield. Willey Series in Probability and Statistics, 2013.
  • A course in time series analysis by Daniel Peña, George C. Tiao, Ruey S. Tsay. Willey Series in Probability and Statistics, 2011.
  • Time series analysis: forecasting and control 4th ed. by Box, George E. P., Jenkins, Gwilym M., Reinsel, Gregory C. Wiley Series in Probability and Statistics, 2008.