[R] The math underlying the `betareg' package?

Gavin Simpson gavin.simpson at ucl.ac.uk
Thu Jan 18 17:34:04 CET 2007

On Thu, 2007-01-18 at 20:00 +0530, Ajay Narottam Shah wrote:
> Folks,
> The betareg package appears to be polished and works well. But I would
> like to look at the exact formulas for the underlying model being
> estimated, the likelihood function, etc. E.g. if one has to compute
> \frac{\partial E(y)}{\partial x_i}, this requires careful calculations
> through these formulas. I read "Regression analysis of variates
> observed on (0,1): percentages, proportions and fractions", by
> Kieschnick & MucCullogh, `Statistical Modelling" 2003, 3:193-213. They
> say that the beta regression that they show is a proposal of theirs -
> is this the same as what betareg does, or is this the Standard
> Formulation?

If you want to know, the best place to look is the source code for the
package, available as a tar.gz file from all good CRAN Mirrors.

I suggest this as the Windows binary might not contain the original
source (i.e unprocessed with comments etc) - I forget now exactly how
the binaries on that platform differ.

> What else should I be reading about beta regressions? :-)

The reference cited in the References section of ?betareg would also be
a good start, esp to understand what the betareg package is doing and
how it compares to the other ref you cite.


 Gavin Simpson                 [t] +44 (0)20 7679 0522
 ECRC, UCL Geography,          [f] +44 (0)20 7679 0565
 Pearson Building,             [e] gavin.simpsonATNOSPAMucl.ac.uk
 Gower Street, London          [w] http://www.ucl.ac.uk/~ucfagls/
 UK. WC1E 6BT.                 [w] http://www.freshwaters.org.uk

More information about the R-help mailing list