nls2 is a set of R functions and programs to estimate the parameters of a non-linear regression model over a given set of observations.
The regression function can be defined explicitly as a function of independent variables and of unknown parameters or it can be defined as the solution of a system of differential equations. Heteroscedasticity of errors can be taken into account by modelling the variance function.
Several additional tools are included: plotting functions, functions to process series of estimations, calculate confidence intervals and confidence regions for parameters and functions of parameters, and process calibration study. The description of the models can be provided by using a symbolic syntax.