Investigating Spectral Analysis in the X-12-ARIMA Seasonal Adjustment Program: Theory and Practice

• Activity Number: 124
• Type: Topic Contributed
• Date/Time: Monday, August 2, 2010 : 8:30 AM to 10:20 AM
• Sponsor: Business and Economic Statistics Section
• Author(s): Wilma S. Jackson*+
• Companies: SAS Institute
• Keywords: Spectral Analysis ; X-12-ARIMA ; Seasonal Adjustment ; ARIMA ; Time Series

Abstract

Spectral analysis in the X-12-ARIMA seasonal adjustment program is used to detect seasonal effects in time series. Seasonal effects in a series being considered for seasonal adjustment indicate that the series should be seasonally adjusted. Seasonal effects in a seasonally adjusted series or the irregular component indicates problems with the seasonal adjustment. The spectral analysis used in X-12-ARIMA is based on work by M.B. Priestly, H. Akaike, and E. Parzen. In this paper, the theoretical basis for the X-12-ARIMA spectral analysis and its implementation in the X-12-ARIMA seasonal adjustment program is investigated. In addition, the effect of the analysis is examined for various series, including some series where the results are unexpected.