In message <[EMAIL PROTECTED]>, Prof Brian Ripley <[EMAIL PROTECTED]> writes
>But Bert's caveats apply: you have 200 problems of size 20,000 since in >QDA each class's distribution is estimated separately, and a single pass >will give you the sufficient statistics however large the dataset is. > I think we've interpreted Bert's question differently. I am not saying I need to have vast amounts of data in RAM, or in a single data structure, or anything like that, and I am not saying I need a 64-bit version of R. What I am saying is that if I had 40 million cases for a problem like the one I described, I'd want to use all of them when designing a classifier. Patrick Burns, if you're reading: OCR = optical character recognition. -- Graham Jones, author of SharpEye Music Reader http://www.visiv.co.uk 21e Balnakeil, Durness, Lairg, Sutherland, IV27 4PT, Scotland, UK ______________________________________________ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html