Publication Abstract

Assessing covariate-dependentcontaminant time-series in the marine environment

R.J. Fryer and M.D. Nicholson

Thispaper describes a method for assessing contaminant time-series when contaminant levelsvary with some covariate and the contaminant-covariate relationship changes over time. Ateach time point, the contaminant data are split into two groups according to whether thecorresponding values of the covariate are smaller or larger than some specified value,leading to two contaminant time-series, for small and large values of the covariaterespectively. Smoothers are then used to model the small and largetime-series, and to construct analyses of variance that test for any change over time, anycovariate effect, and whether the pattern of temporal change in the smalltime-series is the same as in the large time-series. The smoothers can also bedisplayed graphically, allowing easy interpretation of the results. The method is appliedto four time-series of mercury concentrations in fish muscle from monitoring sites aroundthe UK.

Reference:

R.J. Fryer and M.D. Nicholson, 2002. Assessing covariate-dependent contaminant time-seriesin the marine environment. ICES Journal of marine Science, 59(1): 1-14.