Catherine Hood Consulting

Seasonal Adjustment with X-12-ARIMA and TRAMO/SEATS in Windows^®

Purpose:
Seasonal adjustment is an important component of most published monthly and quarterly economic time series and is usually done with off-the-shelf software. Two such programs are X-12-ARIMA (from the U.S. Census Bureau) and SEATS (developed by Agustin Maravall at the Bank of Spain). They are the most widely used programs for seasonal adjustment in the world.

The purpose of this course is to teach participants how to run X-12-ARIMA and SEATS, including its companion ARIMA-modeling program, TRAMO. Topics include writing input files, running the programs, looking at the output, and assessing the results. We will also discuss the purpose of seasonal adjustment and the methods used by the two programs. The course is both practical and technical, and also discusses briefly some theoretical aspects. Involves in-class computer work.

Duration: 3 days

Target audience:
This course is intended for anyone interested in learning how to run X-12-ARIMA and TRAMO/SEATS. The course is limited to 10 persons.

Prerequisites:
None, only general prior knowledge of time series is assumed. Some topics require some knowledge of statistics, for example, the participants should understand terms like mean, covariance, and linear regression.

Benefits to Participants:
Upon completion of the course, the participants will be be able to choose the most appropriate options in X-12-ARIMA and in TRAMO/SEATS, run both programs, and assess the results.

Topics Covered: The course examines the following topics:

• Basic definitions, including time series, seasonal adjustment, trend-cycle, trading day, and moving holidays
• The general syntax of input specification files
• All of the input parameters available in X-12-ARIMA and TRAMO/SEATS
• Running X-12-ARIMA and TRAMO/SEATS in automatic mode and in batch mode
• A review of regARIMA models and the various options available, including the use of TERROR
• A review of the modeling and seasonal adjustment diagnostics available
• Computer work involving a wide range of sample series

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

Note: If time permits at the end of the course, participants will have the chance to work on sample series provided or on their own series. Participants are encouraged to bring sample time series with them to class as either text files or in Excel format.

Windows^® is a registered trademark of Microsoft Corporation

Back to the Top