From: <apjaworski_at_mmm.com>

Date: Tue 16 Aug 2005 - 20:21:32 GMT

Date: Tue 16 Aug 2005 - 20:21:32 GMT

Hi,

I am not sure if this is the right place to report a small typo in one of the manuals. It is not really a bug, is it?.

In any case, at the end of section 11.6.2 (the glm() function) in the Quasi-likelihhod models subsection there is an example of using the glm procedure to fit a particular nonlinear model, which involves model reparametrization. The typo is in the definition of the second variable. It should be x_2 = -1/z_1 and not x_2 = -1/x_1. This appears in two places in the R-intro.texi file in both the R-patched and the R-devel. Fortunately the file diffs are the same for both versions:

5034c5034

< x_1 = z_2/z_1, x_2 = -1/z_1, beta_1 = 1/theta_1, and beta_2 =

---Received on Wed Aug 17 06:25:39 2005

> x_1 = z_2/z_1, x_2 = -1/x_1, beta_1 = 1/theta_1, and beta_2 =

5038c5038 < $x_1 = z_2/z_1$, $x_2=-1/z_1$, $\beta_1=1/\theta_1$ and ---

> $x_1 = z_2/z_1$, $x_2=-1/x_1$, $\beta_1=1/\theta_1$ and

Hope this helps, Andy __________________________________ Andy Jaworski 518-1-01 Process Laboratory 3M Corporate Research Laboratory ----- E-mail: apjaworski@mmm.com Tel: (651) 733-6092 Fax: (651) 736-3122 ______________________________________________ R-devel@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-devel

*
This archive was generated by hypermail 2.1.8
: Mon 24 Oct 2005 - 22:27:37 GMT
*