Do you have questions not answered here? Please send suggestions for other questions to "faq" at catherinechhood.net.
Please also see the Seasonal Adjustment Glossary.
TRAMO/SEATS is a seasonal adjustment program developed by Agustin Maravall and Victor Gomez at the Bank of Spain. TRAMO (Time series Regression with ARIMA noise, Missing observations, and Outliers) and SEATS (Signal Extraction in ARIMA Time Series) are linked programs. TRAMO provides automatic ARIMA modeling, while SEATS computes the components for seasonal adjustment. SEATS uses filters derived from an ARIMA-type time series model that describes the behavior of the series to tailor seasonal and trend filters to the series.
ARIMA model-based signal extraction techniques are based on work by Hillmer/Tiao and Burman.
TRAMO/SEATS is available to download for free from Banco de Espana at the TRAMO/SEATS Download page.
The original TRAMO/SEATS was a DOS program, but there is a Windows version (called TRAMO/SEATS for Windows, or TSW) that works quite well. You choose a series, specify a model, and hit Run. Perhaps the most complicated step is getting the data into a format that TSW can read.
An example data file, one that comes with the TSW installation:
PROD OF MANUFAC METAL (ITALY) 74 1990 1 12 4.5991521 4.7211739 4.6950109 4.6041697 4.7140246 . . .
The first line is the name of the series. The second line contains the number of points in the series (74 points in the example series), the starting year (1990 in the example), the starting month (1 for January), and the period or frequency of the data (in this case, 12 for monthly data).
Once the data is input, the next step is to specify a model. If you don't already know the model, you may want to use an automatic modeling procedure. The automatic modeling options in TRAMO work well.
Dr. Maravall tells me that there is now "a beta version of a COM OBJECT LIBRARY (API)" that will run TRAMO/SEATS from Excel. I haven't tried it yet. I still use Excel macros to export data that I can use in TSW.
SEATS uses ARIMA-model-based signal extraction to estimate the trend and seasonal components. The filters used to calculate these estimates are derived from the ARIMA model fit to the series, usually by TRAMO. This is a very different method than the iterative method used by X-12-ARIMA.
TRAMO/SEATS estimates trading day and moving holiday components as regression effects in regARIMA models. (See question 8 under Definitions and Concepts for a brief description of regARIMA models.) TRAMO adjusts the effects, if any, out of the series before it sends the series to SEATS for the estimation of the trend, irregular, and seasonal components.
If a point is a very large point outlier or a shift in the level of the series, the effect is estimated as a regression effect in the regARIMA model and prior-adjusted out of the series before the iterative procedures begin.
Outliers are adjusted out of the series when estimating the seasonal component so that they don't affect the estimate of the seasonal component. However, they are not adjusted out of the seasonally adjusted series. Point outliers and extreme values are included with the irregular component. Level shifts are included with the trend component. Because the seasonally adjusted series is the trend and irregular components together, all outliers and extreme values are included in the seasonally adjusted series.
TRAMO/SEATS information and documentation can be found at the Bank of Spain website at the TRAMO/SEATS Download page.
Professor Agustin Maravall teaches a limited number of courses each year.
Catherine has taught many courses over the past 14 years. A complete list of the courses available from Catherine is found on the Course List Page.
Once you've read the FAQ (and registered for a class), you should try to run TRAMO/SEATS on your own. We recommend especially TRAMO/SEATS for Windows (TSW) if you are new to TRAMO/SEATS.
(I hope to very soon have a "Getting Started" guide for TSW similar to the guides for X-12-ARIMA.)
Page design by David Joyce at Exit 42 Design
FAQ written by Catherine C.H. Hood
with help from Lynn Imel, Kathy McDonald-Johnson, David Findley, Brian Monsell, and James Ashley
Last modified: 30 Apr 2013