|
Activity Number:
|
52
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Sunday, August 6, 2006 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Business and Economics Statistics Section
|
| Abstract - #306253 |
|
Title:
|
Assessing Spectral Peaks in Economic Time Series
|
|
Author(s):
|
Thomas D. Evans*+ and Stuart Scott and Scott Holan and Tucker S. McElroy
|
|
Companies:
|
Bureau of Labor Statistics and Bureau of Labor Statistics and University of Missouri-Columbia and U.S. Census Bureau
|
|
Address:
|
4561 Sawgrass Court, Alexandria, VA, 22312-3152,
|
|
Keywords:
|
spectral analysis ; labor force statistics
|
|
Abstract:
|
Analysis of spectra is useful in seasonal adjustment of economic time series for identifying the presence of seasonality in observed series and the presence of residual seasonality in seasonally adjusted series. McElroy and Holan (2005) propose a nonparametric test for the presence of spectral peaks. To test this approach, seasonal monthly labor force time series from the U.S. Current Population Survey and simulated seasonal monthly time series will be evaluated for peaks at the seasonal frequencies. Comparisons will be made against other indicators of seasonality: the "visually significant peaks" from X-12-ARIMA, estimated autocorrelations at seasonal lags, and modified F-tests.
|
