Course Description
Autoregressive, moving average, autoregressive-moving average, and integrated autoregressive-moving average processes, seasonal models, autocorrelation function, estimation, model checking, forecasting, spectrum, spectral estimators.
Additional Requirements for Graduate Students:
The graduate students' final project will be more complex and in depth than that of the undergraduate students.
Athena Title
Applied Time Series Analysis
Undergraduate Prerequisite
STAT 4230/6230
Graduate Prerequisite
[STAT 4360/6360 or STAT 4365/6365 or STAT 4360E/6360E and (STAT 4230/6230 or STAT 6315 or STAT 6420)] or permission of department
Semester Course Offered
Offered fall
Grading System
A - F (Traditional)
Course Objectives
The primary objective of this course is to give students a rigorous training in building statistical models for, and drawing inferences from, time series data, which arise naturally in a variety of disciplines. The course will weave several threads together from statistical model building techniques to an in-depth assessment of fitted models, while giving careful consideration to practical issues of model fitting via statistical software (e.g., using SAS). The emphasis is more on analyzing data using various statistical techniques rather than deriving theoretical results. Typically, the course incorporates project assignments as a framework on which students will develop their abilities to think critically about statistical modeling of real data, to use statistical software to analyze real data, and to communicate the findings of their analyses through writing and oral presentation. Technology is integrated into the course through the use of statistical software (e.g., SAS), spreadsheet software (e.g., Excel), internet-based teaching tools (e.g., WebCT), e-mail, and word processing. The course will strive to give students a high degree of competence in analyzing time series data.
Topical Outline
Course topic includes basic tools for identifying characteristics of time series data such as stationarity, non-stationarity, trend, seasonality and variability. Topics such as Autoregressive Integrated Moving Average (ARIMA), Seasonal Autoregressive Integrated Moving Average (SARIMA) and intervention models will be introduced in detail, along with statistical estimation techniques such as maximum likelihood and ordinary least squares. Emphasis will be placed on model diagnostics and assessments.
Syllabus