[R] confint fails in quasibinomial glm: dims do not match

[Peter Ehlers]

Chad,

(inline below)

joris meys wrote:
> Confint doesn't work if you have a multi-dimensional dependent variable.

Well, it will work, but not for the quasibinomial family.

The simple solution would seem to be to change your response from
the matrix cbind(,) to the vector alive/sum(alive+red) and use
the weights=sum(alive+red) argument.

  -Peter Ehlers

> 
> Kind regards
> Joris
> 
> On Fri, Oct 2, 2009 at 4:29 AM, smith_cc <smith_cc at yahoo.com> wrote:
>> I am unable to calculate confidence intervals for the slope estimate in a
>> quasibinomial glm using confint(). Below is the output and the package info
>> for MASS. Thanks in advance!
>>
>> R 2.9.2
>> MASS 7.2-48
>>
>>> confint(glm.palive.0.str)
>> Waiting for profiling to be done...
>> Error: dims [product 37] do not match the length of object [74]
>>> glm.palive.0.str
>> Call:  glm(formula = cbind(alive, red) ~ str, family = quasibinomial,
>> data = subset(master.palive, vtime == 0))
>>
>> Coefficients:
>> (Intercept)         strs
>>       1.05         1.01
>>
>> Degrees of Freedom: 36 Total (i.e. Null);  35 Residual
>> Null Deviance:      20800
>> Residual Deviance: 16200        AIC: NA
>>
>>> packageDescription("MASS")
>> Bundle: VR
>> Contains: MASS class nnet spatial
>> Priority: recommended
>> Version: 7.2-48
>> Date: 2009-07-29
>> Depends: R (>= 2.5.0), grDevices, graphics, stats, utils
>> Suggests: lattice, nlme, survival
>> Author: S original by Venables & Ripley. R port by Brian Ripley
>> <ripley at stats.ox.ac.uk>, following earlier work by Kurt Hornik and Albrecht
>>                Gebhardt.
>> Maintainer: Brian Ripley <ripley at stats.ox.ac.uk>
>> BundleDescription: Functions and datasets to support Venables and Ripley,
>> 'Modern Applied Statistics with S' (4th edition).
>> License: GPL-2 | GPL-3
>> URL: http://www.stats.ox.ac.uk/pub/MASS4/
>> Packaged: 2009-07-31 13:56:57 UTC; ripley
>> Repository: CRAN
>> Date/Publication: 2009-08-05 11:20:53
>> Package: MASS
>> Description: The main library and the datasets
>> Title: Main Package of Venables and Ripley's MASS
>> LazyLoad: yes
>> LazyData: yes
>> Built: R 2.9.2; i686-pc-linux-gnu; 2009-08-25 10:52:10 UTC; unix
>>
>> Cheers,
>> Chad
>> --
>> View this message in context: http://www.nabble.com/confint-fails-in-quasibinomial-glm%3A-dims-do-not-match-tp25709756p25709756.html
>> Sent from the R help mailing list archive at Nabble.com.
>>
>> ______________________________________________
>> R-help at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>>
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
> 
>