Catherine Hood Consulting

Introduction to Seasonal Adjustment

Purpose:
Most of the data published by banks and government agencies consists of time series. When using time series to make decisions, it is often useful to look at time series that have been adjusted for seasonality. It is important to recognize and understand the movements present in time series and to understand the various components of a time series (such as the trend) that are estimated during seasonal adjustment. The course covers the basic concepts needed to understand the uses and mechanics of seasonal adjustment. We will also discuss various software packages available for seasonal adjustment, including how to read output files and diagnostics. This class is only lecture, no computer work required.

Duration: 1 day

Target audience:
This course is intended for a broad audience: managers, decision/policy makers, analysts, economists, and statisticians. No background in time series or seasonal adjustment is required.

Prerequisites: None

Benefits to Participants:
Upon completion of the course, the participants will be able to understand the language of seasonal adjustment, read the output from X-12-ARIMA and/or X-13ARIMA-SEATS, and assess the results from X-12/X-13.

Outline:
The course examines the following topics:

• Basic definitions: time series, seasonal adjustment, trend-cycle, trading day, and moving holidays
• The benefits of using an "off the shelf" program (like X-12-ARIMA or X-13ARIMA-SEATS) for seasonal adjustment
• The general mechanics of seasonal adjustment, such as various types of filters used and multiplicative versus additive adjustment
• Overview of X-12/X-13ARIMA-SEATS, including review of input and output files
• An overview of concepts and the notation of regARIMA modeling, including the basic regressors used for seasonal adjustment
• A review of the diagnostics available, including spectral and stability diagnostics
• A discussion of various issues surrounding seasonal adjustment, including
• Issues with production, including publishing trend-cycles
• Direct versus indirect adjustment of aggregate series
• Possible sources of revisions or changes to the seasonal factors, including a discussion of outliers and extreme values
• Frequency of data collection and issues involved with time consistency and benchmarking
• Other policy issues related to seasonal adjustment

The course will involve the practical application of concepts through the use of case studies, group discussion, and exercises.

---

Trademarks and Copyrights

• TRAMO/SEATS is written by Victor Gomez and Agustin Maravall and is available free of charge from the Bank of Spain web site.
• X-12-ARIMA and X-13ARIMA-SEATS are products of the U.S. Census Bureau and are available free of charge.
• Windows Operating System, Microsoft^® Windows, Copyright Microsoft Corporation