glm.control
Set Control Parameters for Generalized Linear Model
Description
Allows users to set parameters for glm fitting.
Usage
glm.control(epsilon = 1e-08, maxit = 25, trace = FALSE)
Arguments
epsilon |
a numeric value, convergence threshold.
When
abs(new.deviance-old.deviance)/(old.deviance + epsilon) < epsilon
the algorithm is assumed to have converged.
|
maxit |
maximum number of iterations
|
trace |
logical flag: should iteration details be printed while glm() is fitting the model.
|
Value
a list is returned, consisting of the three parameters, epsilon, maxit and trace.
conveniently packaged to supply the control argument to glm(). The values for
glm.control() can be supplied directly in a call to glm(). These
values are then filtered through glm.control() inside glm().
See Also
Examples
glm.control(maxit = 15)