datum.eval: Murray...

In mpoll/scale: The Scaleable Langevin Exact Algorithm -- Reference Implementation

Usage

datum.eval(beta.pos, data.idx)

Arguments

beta.pos
data.idx

Examples

##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

## The function is currently defined as
function (beta.pos, data.idx) 
{
    datum.call <- datum(data.idx)
    datum.z <- exp(sum(datum.call$x * beta.pos))
    log.pi <- datum.call$x * beta.pos * datum.call$y - log(1 + 
        datum.z)
    grad.log.pi <- diag(n.sigma) * datum.call$x * (datum.call$y - 
        datum.z/(1 + datum.z))
    lap.log.pi <- -(diag(n.sigma) * datum.call$x)^2 * datum.z/(1 + 
        datum.z)^2
    list(log.pi = log.pi, grad.log.pi = grad.log.pi, lap.log.pi = lap.log.pi)
  }

mpoll/scale documentation built on Dec. 9, 2019, 7:15 a.m.