alpha.optim:
Optimal value of alpha in Gradient Projection algorithm.
Description
This function gives a value of alpha which guarantees monotone
decrease of the objective function in "obliclus".
Usage
alpha.optim(A, T, G, cluster, info, maxit = 1000)
Arguments
A
The loading matrix for rotation.
T
The current value of rotation matrix.
G
The gradient of the objective function at T on the set of
oblique rotation matrices.
cluster
The vector of cluster parameters which indicate a cluster where each
variable is assigned.
info
The list including an initial value of alpha.
maxit
The limit of the iteration of partial step modification for the
value of alpha.
Value
The value of alpha which is calculated by the partial step
modification described in Jennrich (2002).
References
Jennrich, R.I. (2012). A simple general method for oblique rotation.
$Psychometrika$, 67, 7-20.