Skip to content

adding a new dataset to the default R distribution

2 messages · Stefano Costa, Brian Ripley

Stefano Costa
# 
Hi,
I am a student in archaeology with some interest in statistics and R.

Recently I've obtained the permission to distribute in the public domain
a small dataset (named "spearheads" with 40 obs. of  14 variables) that
was used in an introductory statistics book for archaeologists
(published in 1994).

I've rewritten most of the exercises of that book in R and made them
available at http://wiki.iosa.it/diggingnumbers:start along with the
original dataset, but I was wondering if there is a standard procedure
for getting a new dataset included in the default R distribution, like
"cars" and others.

Please add me to CC if replying because I'm not subscribed to the list.

Best regards,
Stefano
Brian Ripley
#
On Wed, 3 Dec 2008, Stefano Costa wrote:

            

      
      
      
    

        
We will only add datasets to R when they are needed for examples in base R 
(or exceptionally some 'classic' datasets like 'crimtab').  You can always 
distribute a dataset in a package (and many packages do: there are 
several packages on CRAN providing support for books including their 
datasets).