The course covers the fundamentals of modeling time series data, and focuses on the applied use of the three main model types used to analyze univariate time series: exponential smoothing, autoregressive integrated moving average with exogenous variables (ARIMAX), and unobserved components (UCM).

Learn how to

• create time series data
• accommodate trend, as well as seasonal and event-related variation, in time series models
• diagnose, fit, and interpret exponential smoothing models, ARIMAX models, and unobserved components models
• identify relative strengths and weaknesses of the three model types.

Who should attend

Analysts with a quantitative background as well as non-statistical analysts and domain experts who would like to augment their time series modeling proficiency

Formats available	Standard Duration (duration can vary, see event schedule for details)
Classroom:	2.0 days
Live Web Classroom:	4 half-day session(s)
e-Learning:	14 hours/180 day license

Before attending this course, you should have an understanding of basic statistical concepts. You can gain this experience by completing the Statistics 1: Introduction to ANOVA, Regression, and Logistic Regression course.

This course addresses SAS/ETS, SAS Studio software.

Introduction to Time Series

• defining a time series
• using PROC TIMESERIES to transform transactional data into time series data
• define and explore the systematic components in a time series
• describe the decomposition of time series variation
• list three families of time series models
• introduce SAS Studio
• introduce the concepts of white noise and autocorrelation

Exponential Smoothing Models

• exploring weighted average models and exponential smoothing
• comparing and contrasting simple mean, random walk, and exponential smoothing models
• imputing missing values within a time series

ARIMAX Models

• differentiate between ARMA and ARIMA models
• define a stationary time series and identify its importance
• describe and identify autoregressive and moving average processes
• define the differences between a random walk series, a white noise series, and an autoregressive (AR) series
• estimation of autoregressive parameters
• ARMAX and time series regression
• accuracy and forecasting of ARIMAX

Unobserved Components Models

• introduce unobserved components models (UCM) and focus on the multiple sources of error and parameters as a function of time
• describe the basic component models: level, slope, seasonal
• explore the UCM model parameters
• run a UCM model using PROC UCM
• define Random Walk and Linear Trend series
• build a UCM model