search for: schaeferkotter

Dear All, I am using the pmst function from the sn package (version 0.4-0). After inserting the example from the help page, I get non-trivial answers, so everything is fine. However, when I try to extend it to higher dimension: xi <- alpha <- x <- rep(0,27) Omega <- diag(0,27) p1 <- pmst(x, xi, Omega, alpha, df = 5) I get the following result: >p1 [1] 0 attr(,"error")

...orm > distribution, it is called Gauss-Legendre. For the gamma > distribution (including exponential as a special case), the > integral is from 0 to Inf, and it's called Gauss-Laguerre. > Recent references that I found useful for this are the following: > > Kythe and Schaeferkotter (2005) Handbook of > Computational Methods for Integration (Chapman and Hall) > > Evans and Schwartz (2000) Approximating Integrals via > Monte Carlo and Deterministic Methods. > > In theory, one could use Gauss-Jacobi on any finite > interval, Gauss-Laguerre on any...

I've written a series of functions that evaluates an integral from -inf to a or b to +inf using equally spaced quadrature points along a normal distribution from -10 to +10 moving in increments of .01. These functions are working and give very good approximations, but I think they are computationally wasteful as I am evaluating the function at *many* points. Instead, I would prefer to use