Internal function that computes choice coefficients for KRLS given a fixed value for lambda (the parameter that governs the tradeoff between model fit and complexity in KRLS).
This function is called internally by krls. It would normally not be called by the user directly.
Object from call to eigen that contains spectral decomposition of the n by n Kernel matrix.
lambda
Positive scalar value for lamnbda parameter.
eigtrunc
Positive scalar value that determines truncation of eigenvalues for lamnda search window. See krls for details. Default is NULL which means no truncation.
Details
Function relies on fast eigenvalue decomposition method described in method Rifkin and Lippert (2007).
Value
coeffs
n by 1 one matrix of choice coefficients for KRLS model.
Le
n by 1 matrix of errors from leave-one-out validation.
Author(s)
Jens Hainmueller (Stanford) and Chad Hazlett (MIT)
References
Rifkin, Ryan M. and Lippert, Ross A. (2007). Notes on Regularized Least Squares. MIT-CSAIL-TR-2007-025. CBCL-268