Assessing covariate-dependent contaminant time-series in the marine environment

摘要: This paper describes a method for assessing contaminant time-series when levels vary with some covariate and the contaminant-covariate relationship changes over time. At each time point, data are split into two groups according to whether corresponding values of smaller or larger than specified value, leading time-series, small large respectively. Smoothers then used model construct analyses variance that test any change time, effect, pattern temporal in is same as time-series. The smoothers can also be displayed graphically, allowing easy interpretation results. applied four mercury concentrations fish muscle from monitoring sites around UK.