imputeY: impute Y.
In mnbem: Matrix Normal Block EM

given a multivariate normal with mean mu and covariance matrix sig, and a vector of observations y, impute the missing values in y and the corresponding conditional covariance matrix

1	imputeY(y, sig, mu)

`y`
`sig`
`mu`

##---- 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( y, sig, mu )
{
    n <- length( y ); nm < -is.na( y )
    indi <- which( !nm ); v <- matrix( 0, n, n )
    cs <- condiStat( sig, mu, y[indi], indi )
    y[nm] <- cs$cmean; v[nm,nm] <- cs$cdisp
    return( list( yimp = y, vimp = v ) )
  }