Several important economic time series an recorded on a particular day
every week. Seasonal adjustment of such series is difficult because t
he number of weeks varies between 52 and 53 and the position of the re
cording day changes from year to year. In addition certain festivals,
most notably Easter, take place at different times according to the ye
ar. This article presents a solution to problems of this kind by setti
ng up a structural time series model that allows the seasonal pattern
to evolve over time and enables trend extraction and seasonal adjustme
nt to be carried out by means of state-space filtering and smoothing a
lgorithms. The method is illustrated with a Bank of England series on
the money supply.