log_pdtmvn_mode_centered_kernel: Evaluate the kernel function given by the log-pdtmvn mode...

In reichlab/kcde: Kernel conditional density estimation with flexible kernel specifications

Description

Evaluate the kernel function given by the log-pdtmvn mode centered distribution.

Usage

log_pdtmvn_mode_centered_kernel(x, center, bw, bw_continuous,
  conditional_bw_discrete, conditional_center_discrete_offset_multiplier,
  continuous_vars, discrete_vars, continuous_var_col_inds,
  discrete_var_col_inds, discrete_var_range_fns, lower, upper, x_names, log,
  validate_in_support = TRUE, validate_level = 1L, ...)

Arguments

center	a real vector, center point for the kernel function
bw	bandwidth matrix
bw_continuous	the portion of bw corresponding to continuous variables
conditional_bw_discrete	the Schur complement of the portion of bw corresponding to discrete variables
conditional_center_discrete_offset_multiplier	Sigma_dc Sigma_c^-1. This is used in computing the mean of the underlying multivariate normal distribution for the discrete variables conditioning on the continuous variables.
continuous_vars	character vector with names of variables that are to be treated as continuous. May contain entries that do not appear in colnames(x).
discrete_vars	character vector with names of variables that are to be treated as discrete. May contain entries that do not appear in colnames(x)
discrete_var_range_fns	a list with one entry for each element of discrete_vars. Each entry is a named list of length 2; the element named "a" is a character string with the name of a function that returns a(x) for any real x, and the element named "b" is a character string with the name of a function that returns b(x) for any real x.
lower	Vector of lower truncation points
upper	Vector of upper truncation points
log	logical; if TRUE, return the log of the kernel function value
...	mop up extra arguments
a	matrix of values at which to evaluate the kernel function, with column names specified. Each row is an observation, each column is an observed variable.

Value

the value of the kernel function given by the pdtmvn distribution at x.

reichlab/kcde documentation built on May 27, 2019, 4:53 a.m.