mig_loglik_grad function

Gradient of the MIG log likelihood with respect to data

This function returns the gradient vector of the log likelihood with respect to the argument x.

mig_loglik_grad(x, xi, Omega, beta)

Arguments

• x: n by d matrix of quantiles
• xi: d vector of location parameters $\boldsymbol{\xi}$, giving the expected value
• Omega: d by d positive definite scale matrix $\boldsymbol{\Omega}$
• beta: d vector $\boldsymbol{\beta}$ defining the half-space through $\boldsymbol{\beta}^{\top}\boldsymbol{\xi}>0$

Returns

an n by d matrix of first derivatives for the gradient, observation by observation, or a d vector if x is a vector.