IC: The objective function (an information criterion) for...

In xgsu/WOCR: Weighted Orthogonal Components Regression (WOCR) Analysis

Description

The objective function (an information criterion) for optimization in WOCR models.

Usage

IC(lambda, d, gamma, U, y, model = "RR.d.lambda", a = 20,
  criterion = NULL)

Arguments

lambda	The tuning parameter(s) to be optimized. It is 1-D in models RR.d.lambda, RR.gamma.lambda, PCR.d.c, PCR.gamma.c and 2-D in models PCR.d.a.c and PCR.gamma.a.c.
d	The vector of singular values of the design matrix X.
gamma	The vector of coefficients, consisting of the inner product of each orthogonal component and the repsonse y.
U	The U matrix whose columns are the orthogonal components.
y	The response vector y.
model	Specifies the WOCR model to be fitted. Six choices are possible: RR.d.lambda, RR.gamma.lambda, PCR.d.c, PCR.gamma.c, PCR.d.a.c and PCR.gamma.a.c.
a	The fixed shape parameter a in models PCR.d.c and PCR.gamma.c only. By default, a is set to 20.
criterion	Specifies the information criterion to be minimized. The appropriate choice is one from "AIC", "BIC", or "GCV". By default, criterion is left as NULL and the recommended one is used.

Details

This function computes the value of the objective function for the tuning parameter lamdba, depending on which WOCR model is used. See Su et al. (2016+) for the recommended choices. Different models have different weighting strategies and different degrees of freedom. This function is not intended for use outside of this package.

Value

The value of the information criterion as an objective function with respect to the tuning parameter lamdba.

References

• Su, X., Wonkye, Y., Wang, P., and Yin, X. (2016+). Weighted orthogonal component regression (WOCR). Submitted.

See Also

WOCR, weighting

xgsu/WOCR documentation built on May 4, 2019, 1:06 p.m.