|
Activity Number:
|
204
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 13, 2002 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Business & Economics Statistics Section*
|
| Abstract - #301958 |
|
Title:
|
Improving the Automatic RegARIMA Model Selection Procedures of X-12-ARIMA Version 0.3
|
|
Author(s):
|
Kathleen McDonald-Johnson*+ and Catherine Hood and Thuy Trang Nguyen and Brian Monsell
|
|
Affiliation(s):
|
U.S. Census Bureau and U.S. Census Bureau and U.S. Census Bureau and U.S. Census Bureau
|
|
Address:
|
ESMPD, Room 3110/4, Washington, DC, 20233-6200, USA
|
|
Keywords:
|
seasonal adjustment ; regression model with ARIMA errors ; out-of-sample forecast error comparisons
|
|
Abstract:
|
The U.S. Census Bureau has enhanced the X-12-ARIMA seasonal adjustment program by incorporating an improved automatic regARIMA model (regression model with ARIMA errors) selection procedure. The new procedure is based on the automatic model selection procedure of TRAMO, an ARIMA modeling package developed by Victor Gomez and Agustin Maravall. X-12-ARIMA's procedure differs from TRAMO's in a number of ways, related mainly to parameter and likelihood calculation and to outlier identification. We present the results of a study in which we looked at different procedures to estimate trading day, Easter, and outlier effects to possibly improve the ARIMA model chosen by the program. We compared models using goodness-of-fit diagnostics and out-of-sample forecast error comparisons.
|
