Radar target classification typically uses feature sets derived from high range resolution profiles as an input to a classifier. However, such feature sets, when projected in feature space, show both substantial overlap for different targets and substantial variability for a single target. This results in degraded classification performance, as targets cannot be reliably distinguished from one another. In this paper we show that it is a combination of target scattering and signal processing that causes such variability. Specifically we demonstrate that the output of the matched filter is a sensitive function of the relative position of scatters distributed along the length of a target and how this effects the variability of particular features.