Re: [R] lda()

From: Marc R. Feldesman <feldesmanm_at_pdx.edu>
Date: Tue 13 Jul 2004 - 06:03:59 EST

At 08:45 AM 7/12/2004, marzban wrote:
>
>Hello,
>
>For a simple problem with 1 predictor (x) and 2 classes (0 and 1), the
>linear discriminant function should be something like
>
> 2(mu_0 - mu_1)/var x + x-independent-terms
>
>where var is the common variance.
>
>Question 1: Why does lda() report only a single "Coefficients of linear
>discriminants" when there are in fact two coefficients (the x-dependent
>and the x-independent terms)?
>
>Question 2: And how is that single coefficient computed? It is certainly
>not equal to 2(mu_0 -mu_1)/var .
>
>Regards,
>Caren
>--
>http://www.nhn.ou.edu/~marzban

Perhaps some reading would be helpful. I suggest you look first at the help file for lda(). Second, I suggest you read Venables and Ripley, MASS, 4th Edition, where lda() is discussed extensively. Third, I suggest you read Ripley's Pattern Recognition and Neural Networks, where the theory is laid out clearly. Both of these latter books are referenced in lda's help file.

Finally, you might want to tell us what version of lda() you're using, what version of R you're using, and what platform you're running on. For all we know, you're using a 2-year old version of R and lda, both long superceded by vastly improved programs and packages.



R-help@stat.math.ethz.ch mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Tue Jul 13 06:14:49 2004

This archive was generated by hypermail 2.1.8 : Fri 18 Mar 2005 - 02:35:48 EST