[R] summary.negbin broken in R-1.0.0, VR_6.1-7

Prof Brian D Ripley ripley at stats.ox.ac.uk
Thu Mar 30 09:45:38 CEST 2000

On Tue, 21 Mar 2000, Jari Oksanen wrote:

> Dear R people,
> I am not sure if this is the correct place to tell about problems in evolving 
> programmes, but it seems that the `summary.negbin' function of the excellent 
> `MASS' library is now broken, and gives the following error message:

The correct thing to do with contributed code is to tell the porter/author
given in the DESCRIPTION file.  Not all of them read R-help.

> > summary(hm)
> Error in summary.negbin(hm) : subscript out of bounds
> `summary.negbin' calls `summary.glm' which seems to work and give the desired 
> output like called there, but calls to `object["SE"]' fails (and later, if it 
> would get there, `object["th.warn"]' would fail). The first entity seems to be 
> now "SE.theta", and I did not find "th.warn" at all in my objects.

Not really. S has partial matching, so object["SE"] should find 
"SE.theta".  Unfortunately, R's cloning is imperfect here, and it fails.
There is no problem with "th.warn": it is usually missing and does
not cause a failure, as the code is (in print.summary.negbin)

    if (!is.null(x$th.warn)) 
        cat("Warning while fitting theta:", x$th.warn, "\n")

> Really a tiny thing, and if I understood the behaviour correctly, easily to 
> cure by the user herself.

In this case, yes (just replace SE by SE.theta everywhere).  However, there
is a fundamental incompatibility we need to resolve.  It might be
deliberate, but I can't see it is documented.

The next release of VR will have this fixed (and a couple of other things).

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 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch

More information about the R-help mailing list