The mofk() function computes the numerical m-Extent of Shrinkage corresponding to a given value for "k", the scalar that multiplies observed ML estimates of "dMSE"-factors for each of the "p" uncorrelated components in GRR estimation using unr.ridge(). These calculations are quite simple; the function is many-to-one in the sense that all truly large values of k imply that m = 0.0, and k values that are either 0.0 or negative imply that m = p.
mofk(p, k, dMSE)
The integer number of non-constant x-variables used in defining the linear model being fitted to ill-conditioned (intercorrelated, confounded) data. Note that p must also be rank of the given X-matrix.
The given k-factor that multiplies each given dMSE-factor.
Maximum Likelihood estimates of Shrinkage Delta-Factors with minimum MSE risk.
The appropriate scalar value for m:
The computed m-Extent of Shrinkage ...a scalar within [0, p].
Obenchain RL. (2020) Ridge TRACE Diagnostics. https://arxiv.org/abs/2005.14291
Obenchain RL. (2020) The Unrestricted Shrinkage Path: Technical Details. "unrPath.pdf" http://localcontrolstatistics.org