Forecasting Time Series Data
Course Number: 45912
The forecasting course for spring 2019 will be different from previous years.
The course will use the R software package.
Final grades are determined by three components: individual homework assignments, in-class quizzes/tests, and a group project. Groups will be limited to between 2 and 4 students.
The course delivery is in a modified online hybrid format. We will meet on Saturday, March 23 for four hours to start the course. We will then meet, face-to-face, each Monday evenings for two hours. Between the Monday meetings, you will be required to watch video lectures of me explaining the theory and applications.
The Monday meetings will focus on working examples (i.e., use R to create forecasts) and answering questions about your group projects.
The goal of this course is to give students an introduction to the basic time series models. The students will learn the basic summary statistics i.e. autocovariances, trends and seasonal cycles. The course will focus on forecasting observed series and the estimation of both summary statistics and parameters of time series models such as ARMA ARCH and GARCH. The students should be able to interpret the uncertainty in the forecasts and in the estimated parameters.
Diagnostic statistics and model selection criteria will be presented. Observed series will be used to demonstrate the different topics. The students will be graded on a series of individual assignments and a team project. The team project will be in partnership with one other student. The final paper will report estimated models and associated forecasts for an observed time series that the students select. (10/12- FS)
Academic Year: 2019-2020
Semester(s): Mini 4