[R] Poisson/negbin followed by jackknife

[Prof Brian Ripley]

Do you really mean a jackknife or leave-one-out crossvalidation?  They are 
not the same, but the second is often incorrectly called the first.

In either case, I would point you at the book the 'boot' package supports.
See for example its cv.glm function.

On Mon, 7 Nov 2005, Jeffrey Stratford wrote:

> Thanks for the help with the hier.part analysis.  All the problems
> stemmed from an import problem which was solved with file.chose().
>
> Now that I have the variables that I'd like to use I need to run some
> GLM models.  I think I have that part under control but I'd like to use
> a jackknife approach to model validation (I was using a hold out sample
> but this seems to have fallen out of favor).
>
> I'd appreciate it if someone could just point me in the right direction
> for the jackkife analysis given a particular distribution, coefficients,
> etc.

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595