On tests for moving seasonality / by Brajendra C. Sutradhar and Estela Bee Dagum. : CS11-614/91-15E-PDF

"The adjustment of economic and social time series for seasonal variation has been and continues to be the subject of much attention. As a first step towards seasonally adjusting a series, it is essential to test for the presence of stable as well as moving seasonal patterns. The main objective of this paper is to examine the presence of changing seasonal pattern versus a constant seasonal pattern over time. It is shown that the test for the presence of moving seasonality is equivalent to test for the homogeneity of variances of several correlated groups where observations in each group are also correlated. A modification to the standard Bartlett test is proposed which accounts for the autocorrelations. We also develop an asymptotically locally optimal test based on Neyman's (1959) approach. The test procedures are illustrated using the airline series"--Summary.

Lien permanent pour cette publication :
publications.gc.ca/pub?id=9.838524&sl=1

• Format MARC XML
• Format MARC HTML

Demander des formats alternatifs