KRLS v1.0-0

0

0th

Percentile

Kernel-Based Regularized Least Squares

Package implements Kernel-based Regularized Least Squares (KRLS), a machine learning method to fit multidimensional functions y=f(x) for regression and classification problems without relying on linearity or additivity assumptions. KRLS finds the best fitting function by minimizing the squared loss of a Tikhonov regularization problem, using Gaussian kernels as radial basis functions. For further details see Hainmueller and Hazlett (2014).

Functions in KRLS

 Name Description krls Kernel-based Regularized Least Squares (KRLS) lambdasearch Leave-one-out optimization to find $\lambda$ summary.krls Summary method for Kernel-based Regularized Least Squares (KRLS) Model Fits fdskrls Compute first differences with KRLS predict.krls Predict method for Kernel-based Regularized Least Squares (KRLS) Model Fits solveforc Solve for Choice Coefficients in KRLS looloss Loss Function for Leave One Out Error plot.krls Plot method for Kernel-based Regularized Least Squares (KRLS) Model Fits gausskernel Gaussian Kernel Distance Computation No Results!