Hi, I am a researcher in chemistry. I have to do pls-da for some of my samples. The number of variables for my sample is 4000 . The categorical variable has two classes. Some of the values are missing (cant find out). I s there any package for R (or any illustration that would be helpful) to perform PLS-DA in R by ignoring the missing values. Thank you kiran [[alternative HTML version deleted]]
Hi Most methods can somehow deal with NA values. You can find many packages regarding discriminant analysis by simply searching CRAN. discriminant analysis site:r-project.org Or you can look to CRAN task view Multivariate statistics maybe package pls or DiscriMiner does what you want. You can also get rid of NA values by using ?complete.cases function. However I am a bit worried by your number of variables. Regards Petr> -----Original Message----- > From: r-help-bounces at r-project.org [mailto:r-help-bounces at r- > project.org] On Behalf Of kiran subedi > Sent: Monday, July 15, 2013 4:51 AM > To: r-help at r-project.org > Subject: [R] (no subject) > > Hi, > I am a researcher in chemistry. I have to do pls-da for some of my > samples. > The number of variables for my sample is 4000 . The categorical > variable has two classes. Some of the values are missing (cant find > out). > I s there any package for R (or any illustration that would be helpful) > to perform PLS-DA in R by ignoring the missing values. > > > Thank you > kiran > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help at 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.
Look at the package chemometrics, it can certainly handle your number of variables (p > n is what that's called and it requires special considerations). I don't recall about missing values. The authors of that package also have a very helpful text. Good Luck. Bryan On Jul 14, 2013, at 10:50 PM, kiran subedi <keasans at gmail.com> wrote:> Hi, > I am a researcher in chemistry. I have to do pls-da for some of my samples. > The number of variables for my sample is 4000 . The categorical variable > has two classes. Some of the values are missing (cant find out). > I s there any package for R (or any illustration that would be helpful) to > perform PLS-DA in R by ignoring the missing values. > > > Thank you > kiran > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help at 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.