The most fundamental seasonal adjustment deficiency is detectable seasonality after adjustment. Residual seasonality has reduced amplitudes and other properties which make it necessary to undertake its detection differently from seasonality detection in unadjusted series. We present the results of our investigation of residual seasonality detection properties of three types of diagnostics, regression, spectrum and positive seasonal autocorrelation, six diagnostics in all. These are available, sometimes with modifications, in widely used software, five in TRAMO-SEATS, X-13ARIMA-SEATS and JDemetra+, one only in JDemetra+. All were applied to a set of sixteen underadjusted U.S. Census Bureau Monthly Retail Trade Survey series. The series have evidence of changing seasonality but were deliberately adjusted only for stable seasonality. Residual seasonality was found in the final 8 years of all series and all but one irregulars series. Patterns of "weak" and "strong" detections differ by diagnostic and final span length, sometimes in quite complementary ways.

Others in Series

Working Paper

Detection of Seasonality in the Frequency Domain

January 11, 2017

Detection of Seasonality in the Frequency Domain

Working Paper

Maximum Entropy-Value Seasonal Adjustment

January 11, 2017

Maximum Entropy-Value Seasonal Adjustment

Working Paper

Holiday Effects in Indian Manufacturing Series

August 10, 2017

Holiday Effects in Indian Manufacturing Series

View All

Related Information

WORKING PAPER

Statistical Research Reports and Studies

Time Series and Seasonal Adjustment Working Papers

Page Last Revised - October 28, 2021

Some content on this site is available in several different electronic formats. Some of the files may require a plug-in or additional software to view.

Is this page helpful?
Thumbs Up Image

Yes

NO THANKS

255 characters maximum

255 characters maximum reached

Thank you for your feedback.
Comments or suggestions?

Top