mig_kdens function

Multivariate inverse Gaussian kernel density estimator

Given a matrix of new observations, compute the density of the multivariate inverse Gaussian mixture defined by assigning equal weight to each component where $\boldsymbol{\xi}$ is the location parameter.

mig_kdens(x, newdata, Omega, beta, log = FALSE)

Arguments

• x: n by d matrix of quantiles
• newdata: matrix of new observations at which to evaluated the kernel density
• Omega: d by d positive definite scale matrix $\boldsymbol{\Omega}$
• beta: d vector $\boldsymbol{\beta}$ defining the half-space through $\boldsymbol{\beta}^{\top}\boldsymbol{\xi}>0$
• log: logical; if TRUE, returns log probabilities

Returns

value of the (log)-density at newdata