JSM 2004 - Toronto

Abstract #300899

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2004 Program page
Activity Number: 108
Type: Topic Contributed
Date/Time: Monday, August 9, 2004 : 10:30 AM to 12:20 PM
Sponsor: Business and Economics Statistics Section
Abstract - #300899
Title: Span Diagnostics for Model-based Seasonal Adjustment
Author(s): Roxanne Feldpausch*+ and Kellie Wills and Catherine Hood
Companies: U.S. Census Bureau and U. S. Census Bureau and U.S. Census Bureau
Address: 4700 Silver Hill Rd., Washington, DC, 20233,
Keywords: signal extraction ; spectrum diagnostics ; ARIMA models
Abstract:

We investigate diagnostics for determining whether a series is suitable for ARIMA model based (AMB) seasonal adjustment. Since model inadequacy can lead to inadequacies in the AMB decomposition, evaluating model fit is an essential part of AMB seasonal adjustment. We investigate how effectively two model-fit diagnostics--ACF and Ljung-Box Q--identify series for which AMB seasonal adjustment will be problematic. If the process generating the data changes over time, the ARIMA model chosen for the full data may be inappropriate for some time period, leading to instability of the adjustment. We evaluate model fit in overlapping spans of data to detect situations in which adding or subtracting small amounts of data results in poor fit. We also consider the use of spectrum peaks to identify data spans that do not have detectable seasonality, as well as changes in the trading day pattern. We present results from data simulated from known ARIMA models, as well as real data examples.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2004 program

JSM 2004 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2004