[adegenet-forum] xvalDapc and group prediction accuracy

[Mark Coulson]

Hello,

I am using xvalDapc on a dataset and it produces a nice arc-shape with the optimal number of PCs retained at 20. However, if I run the dapc function keeping 20 PCs, I get the warning that

'#PCs may be too large (>N/3) and that results may be unstable'

How should I interpret this given the choice to use 20 PCs was through the double-cross validation procedure?

Thanks,
Mark
Inverness College UHI, a partner in the University of the Highlands and Islands www.inverness.uhi.ac.uk Board of Management of Inverness College (known as Inverness College UHI), Scottish Charity No SC021197.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/adegenet-forum/attachments/20170925/8e3033d3/attachment.html>