I remember doing this some time ago but forgot. Perhaps this might help
you
MASS:::predict.lda
On Tue, 2004-07-13 at 23:56, marzban wrote:> Hi.
>
> I asked a question about lda() and got some answers. However, one
> question remains (which is not independent of the earlier ones):
>
> What output does lda() produce which I can use to compute the
> posteriors? I know predict(lda())$posterior will give me precisely the
> posteriors, but suppose I'd like to compute them myself, outside
> of R.
>
> So far, I have not been able to use "coefficients of linear
> discrimiants" to do this, for they don't seem to be the alpha and
beta
> in log(post) ~ alpha x + beta (this eqn being a caricature of
> LDA in Ripley).
>
> Caren