To estimate the information transmitted across a neuronal sensory system one has to deal with serial dependence among consecutive samples of the stimulus and the response signal. Common methods usually require a huge amount of data, or are restricted to Gaussian stimuli. Here, we describe stimulus and response as stochastic processes, i.e. as sequences of random variables, in the same coordinate system. Stimulus-response pairs of these random variables must not be considered independently because otherwise the transinformation is overestimated. To account for the linear fraction of the serial dependence, we present two decorrelation techniques based on coordinate transformation. They provide a representation of the processes with uncorrelated random variables and yield a more precise estimate of the transinformation.