Calc.F.cond: Conditional Distribution calculation at the data points

In rohitpatra/BrownCondInd: Nonparametric Notion of Residual and Test for Conditional Independence

Description

Conditional Distribution calculation at the data points

Usage

Calc.F.cond(x, y, z, z.dim, bwmet, bwobj = NULL)

Arguments

x	A numeric vector of observations of x
y	A numeric vector of observations of y
z	A numeric matrix of observations of z
z.dim	Dimension of z, number of columns ofz matrix
bwmet	which method to use to select bandwidths. cv.ls specifies least-squares cross-validation, and normal-reference just computes the ‘rule-of-thumb’ bandwidth hj using the standard formula hj = 1.06σj n−1/(2P +l) , where σj is an adaptive measure of spread of the jth continuous variable defined as min(standard deviation, mean absolute de- viation/1.4826, interquartile range/1.349), n the number of observations, P the order of the kernel, and l the number of continuous variables. Note that when there exist factors and the normal-reference rule is used, there is zero smoothing of the factors. Defaults to cv.ml.
bwobj	should be of the kind that is returned from Calc.F.cond. Use it in case you want to use previously calculated bandwdiths (from other data points) to evaluate the estimate the conditional distribution functions from (x,y,z). Default is NULL. In that case uses ‘bwmet' to compute this#’

Value

A list including the elements:

F.x_z	Estimate of conditional distribution of X|Z
F.y_z	Estimate of conditional distribution of Y|Z
Fbw.x_z	Bandwidths used for computation of conditional distribution of x|z
Fbw.y_z	Bandwidths used for computation of conditional distribution of y|z
Fbw.z_z	Bandwidths used for computation of conditional distribution of z|z
F.z_hat	Estimate of conditional distribution of Z_d|Z_1,..,(d-1), Z_d-1|Z_1..(d-2),..., Z_2|Z_1,

rohitpatra/BrownCondInd documentation built on Feb. 25, 2021, 3:03 p.m.