An alternative computational algorithm for calculating the nonlinearity of regression models with two parameters

This paper presents an alternative computational algorithm for finding the root mean square (RMS) curvature as a nonlinearity measure of nonlinear regression model (NLR model) with two parameters. Specially, the suggested algorithm is applied on a NLR model in which there is a conditionally linear parameter. The algorithm is mainly based on the work presented in [ D.M. Bates, D.G. Watts, Relative curvature measures of nonlinearity (with discussion), Journal of the Royal Statistical Society 42 (1) (1980) 1- 25]. The algorithm is suited for implementation using computer algebra systems (CAS) such as MAPLE, MATLAB, MACSYMA and MATHEMATICA. The researchers compare the results with the corresponding output of the S-PLUS Program for the same considering example and the results in some earlier works.