NLIN Procedure
The NLIN procedure fits nonlinear regression models and estimates the parameters by nonlinear least squares or weighted nonlinear
least squares. You specify the model with programming statements. This gives you great flexibility in modeling the relationship
between the response variable and independent (regressor) variables. It does, however, require additional coding compared to model
specifications in linear modeling procedures such as the REG, GLM, and MIXED procedures. The following are highlights of the NLIN
procedure's features:
 provides a highquality automatic differentiator so that you do not need to specify first and second derivatives. You can, however, specify the derivatives if you wish.
 solves the nonlinear least squares problem by one of the following four algorithms (methods):
 steepestdescent or gradient method
 Newton method
 modified GaussNewton method
 Marquardt method
 enables you to confine the estimation procedure to a certain range of values of the parameters by imposing bounds on the estimates
 computes Hougaard's measure of skewness

 provides bootstrap estimates of confidence intervals for parameters and the covariance/correlation matrices of the parameter estimates
 performs weighted estimation
 creates an output data set that contains statistics that are calculated for each observation
 creates a data set that contains the parameter estimates at each iteration
 performs BY group processing, which enables you to obtain separate analyses on grouped observations
 creates a SAS data set that corresponds to any output table
 automatically created graphs by using ODS Graphics

For further details see the SAS/STAT User's Guide:
The NLIN Procedure
( PDF  HTML )
Examples