[R] bivariate normal

Rolf Turner rolf.turner at xtra.co.nz
Sat Jul 28 00:46:12 CEST 2012

On 28/07/12 05:45, Anders Holm wrote:
> Dear list members
> I need a function that calculates the bivariate normal distribution for each observation. It is part of a likelihood function and I have 1000's of cases. As I understand it I cannot use packages like "mvtnorm" because it requres a covariance matrix of the same dimension as the number of observations.

     Huh?  Where ever did you get that idea?  (Makes no sense at all,
     as far as I can see.)
> Basically what I need is a function that takes as arguments a n*2 matrix of bivariate values given a common mean and covariance matrix, where n is the number of cases and which returns a n*1 vector of the probabilities of the bivariate normal distribution of the n*2 vector of values.

     Sorry, I must be a bit dim, but I don't follow this at all.

     Anyhow, either dmnorm() from the "mnormt" package or
     dmvnorm() from the "mvtnorm" package should, properly applied,
     do everything that you want.



More information about the R-help mailing list