ramseyd@landcareresearch.co.nz
2004-May-24 05:01 UTC
[Rd] bug in extractAIC.survreg (PR#6910)
Full_Name: Dave Ramsey Version: 1.8.0 OS: win2000 Submission from: (NULL) (202.27.240.6) there is a bug in extractAIC.survreg in library MASS. A survreg model object has no component called "residuals". Hence n <- length(fit$residuals) returns 0 resulting in errors workaround: replace n <- length(fit$residuals) with n <- length(residuals(fit)) ### sorry: error in my email address on previous posting
The currrent version of R is 1.9.0, and that has public patches which say (in the NEWS file) o extractAIC.survreg() needed updating. The R posting guide does ask you to check the latest version before wasting people's time. It is a double waste of time to send this twice (as 6909 as well): please do read the description of how to add to a previous report. On Mon, 24 May 2004 ramseyd@landcareresearch.co.nz wrote:> Full_Name: Dave Ramsey > Version: 1.8.0 > OS: win2000 > Submission from: (NULL) (202.27.240.6) > > > there is a bug in extractAIC.survreg in library MASS.extractAIC.survreg is not in *package* MASS:> getAnywhere("extractAIC.survreg")A single object matching 'extractAIC.survreg' was found It was found in the following places registered S3 method for extractAIC from namespace stats namespace:stats with value function (fit, scale, k = 2, ...) { edf <- sum(fit$df) c(edf, -2 * fit$loglik[2] + k * edf) } <environment: namespace:stats> Had you thought so, you should have communicated with the package maintainer (and told him the package version).> A survreg model object has no component called "residuals". Hence > > n <- length(fit$residuals) > > returns 0 resulting in errors > > workaround: replace > > n <- length(fit$residuals) > > with > > n <- length(residuals(fit)) > > ### sorry: error in my email address on previous posting > > ______________________________________________ > R-devel@stat.math.ethz.ch mailing list > https://www.stat.math.ethz.ch/mailman/listinfo/r-devel > >-- Brian D. Ripley, ripley@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