Abstract
The use of Generalized Additive Models in the analysis of Continuous Plankton Recorder (CPR) distribution and abundance data for C alanus finmarchicus and C. helgolandicus is demonstrated. Strong emphasis is placed on the influence of long‐term trend, seasonality and location. The preponderance of zeros in the data, as well as the particular problems associated with the CPR recording protocol, are adequately handled by the models. Three models are described. In the first two, data within arbitrary spatial compartments are modelled as smooth functions of long‐term trend and seasonality, assuming a spatial homogeneity within the area. In the third model, the spatio‐temporal distributions of abundances over the North Sea in specific months each year are modelled as a three‐dimensional smooth function of long‐term trend and location (latitude and longitude). The summaries produced by the models reveal dynamic seasonal, spatial and long‐term patterns of abundance, many of which have not been revealed by the previous analytical techniques employed.