Select the step size for numerical differentiation.
Syntax
nds = nuderst(pars)
Description
The function pem uses numerical differentiation with respect to the model parameters when applied to state-space structures. The same is true for the functions th2ff and th2zp when the parameter covariance information is translated to frequency function and zero-pole accuracy (again only for state-space structures). Finally, the command thd2thc uses numerical differentiation when translating the covariance information for any model structure.
The step size used in these numerical derivatives is determined by the M-file nuderst. The output argument nds is a row vector whose k-th entry gives the increment to be used when differentiating with respect the k-th element of the parameter vector pars.
The default version of nuderst uses a very simple method. The step size is the maximum of 
and 
times the absolute value of the current parameter. You can adjust this to the actual value of the corresponding parameter by editing nuderst. Note that the nominal value, for example 0, of a parameter may not reflect its normal size.
[ Previous | Help Desk | Next ]