4 messages · trindade@stat.ufl.edu, Brian Ripley, Peter Dalgaard
There is a mistake on the "Weibull Distribution" (base package) help page in the online docs (http://docs.stat.ufl.edu/R/doc/html/). The formula for Var(X) should have Gamma(1 + 1/a)^2 in place of Gamma(1 + 1/a).
Alex Trindade Assistant Professor of Statistics University of Florida http://www.stat.ufl.edu/personnel/usrpages/trindade.shtml
That is a mistake at your own department's site, but not in the current R sources. It seems those docs are from R 1.2.2! Even R 1.6.2 has the correct formula. Please ask whoever maintains that site to correct it, and don't expect the R team to fix problems in 3.5 year old versions of R.
There is a mistake on the "Weibull Distribution" (base package) help page in the online docs (http://docs.stat.ufl.edu/R/doc/html/). The formula for Var(X) should have Gamma(1 + 1/a)^2 in place of Gamma(1 + 1/a).
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
trindade@stat.ufl.edu writes:
There is a mistake on the "Weibull Distribution" (base package) help page in the online docs (http://docs.stat.ufl.edu/R/doc/html/). The formula for Var(X) should have Gamma(1 + 1/a)^2 in place of Gamma(1 + 1/a).
Looks like docs.stat.ufl.edu haven't been updated for a while. It still has the old organisation of the base packages. We can't fix bugs retrospectively, y'know... The 1.9.1 version does have the squared term (it has gamma instead of Gamma, though).
O__ ---- Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~~~~~~~~~ - (p.dalgaard@biostat.ku.dk) FAX: (+45) 35327907
Prof Brian Ripley <ripley@stats.ox.ac.uk> writes:
That is a mistake at your own department's site, but not in the current R sources. It seems those docs are from R 1.2.2! Even R 1.6.2 has the correct formula. Please ask whoever maintains that site to correct it, and don't expect the R team to fix problems in 3.5 year old versions of R.
Now that we have a PR#, maybe we should record a wishlist item that the formatted docs should include the version of R for which they were generated?
O__ ---- Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~~~~~~~~~ - (p.dalgaard@biostat.ku.dk) FAX: (+45) 35327907