Time Series

Catalog description

The course introduces the student to the statistical analysis of time series data. The covered topics include: autocorrelation; stationarity, basic time series models; autoregressive (AR), moving-average (MA) and ARMA; trend removal and seasonal adjustment; invertibility; spectral analysis; estimation, data analysis and forecasting with time series models; forecast errors and confidence intervals; introduction to financial time series and autoregressive conditional heteroskedasticity (ARCH) models The materials will partially cover the syllabus of SOA Exam Statistics for Risk Modeling and that of Exam Predictive Analytics. Prerequisites: C or better in MATH 448 and in one of the following: MATH 329, MATH 445, MATH 446, DIDA 325, or a similar computing course approved by the Director of Undergraduate Studies (DUS); or consent of instructor. Must have junior or senior standing.