Three different heat treatments of aluminum alloy AA5052 were subjected to various levels of uniaxial plastic strain. The resulting surfaces were then evaluated using both scanning laser confocal microscopy (SLCM) and stylus profilometry. Three regression approaches were used to assess the quality of a linear and a curvilinear fit for the roughness data as a function of true plastic strain. While there were differences among the regression results, the analyses revealed that a linear model was more statistically appropriate for the finest grain size. As the grain size increased, the surface morphology became more complex and a quadratic model became more suitable. Since the relative area fractions of grain boundary-localized roughness and slip-induced roughness are grain size dependent, the higher order fit between the roughness and plastic strain reflects substantial changes in the ratio of these areas. The differences between the SLCM and profilometry results were attributed to the natural filtering that occurs during contact profilometry. This filtering skewed the roughness data toward the largest surface displacements, thereby reducing the measurement fidelity to the point where the only possible outcome was the linear relationship.