MCV_grid: Modified cross-validation

In hoangtt1989/NOIS: Non-parametric Outlier Identification and Smoothing

Description

Evaluate modified cross-validation (MCV) for the Nadaraya-Watson estimator over a grid

Usage

MCV_grid(x, y, m_brk = 0.6, a = 0.75, b = 10, eps0 = 1/175,
  gridlen = 100, weight_probs = c(0.05, 0.95))

Arguments

x	'x' values.
y	'y' values.
m_brk	The fraction of observations used for training. This is the most sensitive parameter.
a	Constant for tuning grid (not recommended to change).
b	Constant for tuning grid (not recommended to change).
eps0	Constant for tuning grid (not recommended to change).
gridlen	The number of grid points.
weight_probs	Specification for what percentage of points are used in the weight function.

Value

The minimum bandwidth h, the minimum CV error and the grid of test bandwidths.

See Also

Other NOIS CV functions: LOOCV_grid, NOIS_fit, PCV_grid

hoangtt1989/NOIS documentation built on May 20, 2019, 2:08 p.m.