The annual series aggregated from a seasonal series which is generated
by a periodic AR(1) or ARMA(1,1) model is considered and the moments
(variance and covariances) associated with the annual series are exami
ned. It is found that the performance of the aggregated series in repr
oducing the historical moments depends on the type of periodic model a
nd the number of seasons in a year. Only the annual series aggregated
from a seasonal series which is generated by a two-season AR(1), two-s
eason ARMA(1,1) or three-season ARMA(1,1) model can exactly preserve t
he historical variance, when the parameters of the periodic model are
estimated using the method of moments.