nlminb.control(eval.max, iter.max, abs.tol, rel.tol, x.tol,
               step.min, step.max, scale.init, scale.upd,
               scale.fac, scale.tol, scale.mod, sing.tol,
               sing.step, diff.g)

eval.max=:

limit on the number of evaluations of the residual functions. Default : 200.

iter.max=:

limit on the number of iterations. Default : 150.

abs.tol=:

absolute function convergence tolerance. Default : 10^(-20).

rel.tol=:

relative function convergence tolerance. Default : max( 10^(-10), .Machine$double.eps^(2/3))

x.tol=:

parameter convergence tolerance. Default : .Machine$double.eps^(1/2)

step.min=:

minimum scaled steplength (false convergence tolerance). Default : 100*.Machine$double.eps

step.max=:

initial scaled step bound. Default : 1.0

scale.init=:

a scalar value controlling the initial value of the scale. If scale.init >= 0, all components of the scale vector will be initialized to scale.init before updating. If scale.init < 0, the scale vector will not be initialized internally. Default : 0.0

scale.upd=:

controls automatic updating for parameter scaling. Possible values are 0 (no updating of the initial scale vector), 1 (update the scale vector at every iteration), 2 (update the scale vector only at the first iteration). Default : 0

scale.fac=:

a scalar value used in automatic updating of scale at the beginning of an iteration. Each component of scale is set either to the norm of the corresponding diagonal element of the Hessian matrix or else to scale.fac times its current value, whichever is larger. Default : 0.6

scale.tol=:

scalar values controlling resetting small components of scale during automatic updating. If a component of scale becomes smaller than scale.tol in magnitude, it is set to scale.mod. Default : scale.tol = 10^(-6).

scale.mod=:

scalar values controlling resetting small components of scale during automatic updating. If a component of scale becomes smaller than scale.tol in magnitude, it is set to scale.mod. Default : scale.mod = 1.0.

sing.tol=:

tolerance used in singular convergence test. Default : sing.tol = max( 10^(-10), .Machine$double.eps^(2/3))

sing.step=:

step used in singular convergence test. Default : sing.step = 1

diff.g=:

step size parameter for finite-difference gradient approximations, which should approximate the relative error in computed values of the objective. Default : .Machine$double.eps^(1/2)

nlminb.control would normally be called only to set the control parameter in a call to nlminb. Names may not be abbreviated.

nlminb(start = ex.start, obj = ex.f, grad = ex.g,
       control = nlminb.control( iter.max = 100, x.tol = .0001),
       y = ex.y, z = ex.z)