|
Activity Number:
|
342
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 6, 2003 : 9:00 AM to 10:50 AM
|
|
Sponsor:
|
Business & Economics Statistics Section
|
| Abstract - #301266 |
|
Title:
|
Towards X-13?
|
|
Author(s):
|
Brian C. Monsell*+ and John Aston and S. J. Koopman
|
|
Companies:
|
U.S. Census Bureau and NISS/U.S. Census Bureau and
|
|
Address:
|
317 Ethan Allen Ave., Takoma Park, MD, 20912-4527,
|
|
Keywords:
|
model-based signal extraction ; component time series models ; seasonal adjustment diagnostics ; graphical diagnostics ; revisions
|
|
Abstract:
|
In collaboration with the current developers of the SEATS seasonal adjustment program, an experimental version of X-12-ARIMA that produces model based seasonal adjustments from SEATS has been developed. This program allows users to generate X-11 and SEATS seasonal adjustments using the same interface, and compare these seasonal adjustments using a common set of diagnostics. This poster will demonstrate how SEATS adjustments are integrated into the X-12-ARIMA procedure, and show examples of the types of seasonal adjustment and graphical diagnostics available for model based seasonal adjustments. Another possibility is to use component time series models to perform the signal extraction. These models include those of SEATS but also structural time series models such as those developed by Andrew Harvey. A flexible implementation allowing easy specification of different models has been developed using the SsfPack software module of the Ox matrix programming language. This will also allow the incorporation of heavy tailed distributions into certain components within the model. Examples of robust seasonal adjustments using this method will be shown.
|
