The resilient modulus ( Mr) is typically interpreted as the average of the last five secant slopes of the cyclic stress-axial resilient strain curve from repeated loading triaxial tests. It is not uncommon to then fit mathematical models to the secant Mr to derive model parameters ( Ki, more commonly known as K1, K2, and K3) that are then used in pavement analysis. Some engineers also backcalculate Ki from a falling weight deflectometer test. Many researchers use an incremental loading procedure to analyze pavements. When doing so, it is important to consider the nonlinear load-deformation behavior, which is considered only coarsely in the secant slope approach. Some incremental loading procedures assume the geomaterial to be nonlinear elastic while a dynamic finite element analysis typically assumes the geomaterials to be nonlinear and viscoelastic, that is, having springs and dashpots. With the latter, additional damping parameters to represent the viscoelastic effects are required. This paper compares Ki parameters estimated using linear regression on a log transformation of the Mechanistic–Empirical Pavement Design Guide (MEPDG) Mr model, which is a non-viscoelastic secant Mr approach, with those obtained using nonlinear regression of the time dependent deformations when interpreting the Mr test using incremental loading of a: 1) nonlinear elastic geomaterial; and 2) nonlinear viscoelastic geomaterial with inertial mass. The results show that the estimated Ki parameters governing the geomaterial nonlinearity are substantially affected by the estimation method and that the second alternative approach can model hysteresis well.