Thanks Bill,
Yes in my data too I get some different posteriors also. I guess what I was
getting at was that when I'm dealing with multi-elemental data with 16
variables a probability of 1 is a bit more "certain" an assignment than I
was expecting. I'm a student, so perhaps I don't have quite the handle on
the theory that I should. I'm attempting to explain some of the
classifications in my write-up so was just looking for some discussion
really.
Thanks for your help.
Gareth Campbell
PhD Candidate
The University of Auckland
P +649 815 3670
M +6421 256 3511
E gareth.campb...@esr.cri.nz
gcam...@gmail.com
2009/4/12 <bill.venab...@csiro.au>
> If you try
>
> library(MASS)
> example(lda)
> predict(z)$posterior
>
> You will see there are very many posterior probabilities there, too, which
> differe from 1 by round-off error at most. So your data are not unique.
>
> I don't get why you don't get it.
>
>
> Bill Venables
> http://www.cmis.csiro.au/bill.venables/
>
>
> -----Original Message-----
> From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org]
> On Behalf Of gcam032
> Sent: Sunday, 12 April 2009 11:16 AM
> To: r-help@r-project.org
> Subject: [R] predict.lda posteriors equal to 1
>
>
> Hi all,
>
> I was wondering if anyone was able to explain to me why when I run
> predict.lda() on some new data I get lots of posterior probabilities = 1.
> This seems markedly unrealistic. What do the posteriors mean in the
> context
> of the predict.lda() function?
>
> Thanks
>
> Gareth
> --
> View this message in context:
> http://www.nabble.com/predict.lda-posteriors-equal-to-1-tp23007165p23007165.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
