|
Activity Number:
|
262
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Business and Economics Statistics Section
|
| Abstract - #307980 |
|
Title:
|
Recasting X11 Seasonal Adjustment Filters into Smoothers
|
|
Author(s):
|
Tucker S. McElroy*+ and Agustin Maravall
|
|
Companies:
|
U.S. Census Bureau and Bank of Spain
|
|
Address:
|
4700 Silver Hill Road, Washington, DC, 20233-9100,
|
|
Keywords:
|
ARIMA model ; nonstationary time series ; seasonal adjustment
|
|
Abstract:
|
Two unsolved problems with the X-11 seasonal adjustment methodology are the construction of standard errors and the handling of the boundaries. We adapt the ``implied model approach" of Kaiser and Maravall (2005) to achieve both objectives, while using two different assumptions on the given generic filter. Namely, we consider either that it is an output-matching filter or that it is a Wiener-Kolmogorov (WK) filter. For both approaches we lay out the explicit assumptions that are necessary, and the resulting algorithms for generating smoothers. The methods are then applied to the X11 seasonal adjustment, trend, and irregular filters. We then produce time-dependent signal extraction Mean Square Errors for the X11 estimates.
|
