Bulletin Description
Prerequisites: MATH 228*, MATH 325*, and MATH 440* all with grades of C or better; or permission of the instructor.
Introduction to the theory and practice of time series analysis. Topics include time series regression and exploratory data analysis, stationary processes, ARMA/ARIMA models, Spectral analysis, and Multivariate time series analysis: Multivariate ARMA. The analyses will be performed using R/Python software.
Course Objective
Learn basic analysis of time series data; learn basic concepts in time series regression; learn auto-regressive and model averaging models; learn basic concepts of spectral analysis, and utilize R/Python for computation, visualization, and analysis of time series data.
Course Description
This course introduces the theory and practice of time series analysis. Topics include time series regression and exploratory data analysis, stationary processes, ARMA/ARIMA models, Spectral analysis, Multivariate time series analysis: Multivariate ARMA. The Analyses will be performed using R/Python software. Topics covered include:
- Basic ideas of time series analysis and stochastic processes
- Exploratory data analysis
- Time series regression, elimination of trend and seasonal component
- Stationary processes: properties, linear processes, estimating the mean and autocovariance functions.
- ARMA models: ACF, PACF.
- Modeling and forecasting with ARMA processes: estimation and forecasting.
- Nonstationary time series: ARIMA models.
- Spectral Analysis of time series.
- Evaluation of students
Students will be graded on quizzes, homework assignments, data analysis project, and examinations.
Textbook and software
Time Series Analysis and Its Applications With R Examples, Fourth Edition, by R. H. Shumway and D. S. Stoffer, Springer. An e-version available for free.
Software: R and Python