This one-day course will be offered via Zoom only. Course schedule is 10:00am – 4:00pm, with a 1 hour lunch and (2) 10 minute breaks (1 in morning and 1 in afternoon). Attendance is required as it will not be recorded.

Description: 
This course will be a brief and thorough introduction to modern methods of time series analysis. Topics to be covered include elementary time series models, trend and seasonality, stationary processes, autoregressive/integrated/moving average (ARIMA) processes, fitting ARIMA models, forecasting, spectral analysis, the periodogram, spectral estimation techniques, multivariate time series. Additional topics may be covered if time permits. Some applications will be provided to illustrate the usefulness of the techniques.

Prerequisites:
Course in probability and statistics and familiarity with matrix theory and linear algebra.

Course Goals:
This course will provide students with a theoretical foundation in the analysis of time series in the time domain including identification, estimation, and prediction in several well-established time series models.

Course Objectives:
By the end of the course, you will be able to:
• Analyze datasets to construct plausible time series models
• Estimate parameters of ARMA and ARIMA models
• Model and forecast with ARMA, ARIMA and SARIMA processes
• Analyze multivariate time series models