Hi all, Suppose I have 2 matrices A and B. And I want to measure how good each of this matrix is. So I intend to compare A and B with another "gold standard" matrix X. Meaning the more similar a matrix to X the better it is. What is the common way in R to measure matrix similarity (ie. A vs X, and B vs X) ? - Gundala Viswanath Jakarta - Indonesia
Gundala Viswanath wrote:> Hi all, > > Suppose I have 2 matrices A and B. > And I want to measure how good each of this matrix is. > > So I intend to compare A and B with another "gold standard" > matrix X. Meaning the more similar a matrix to X the better it is. > > What is the common way in R to > measure matrix similarity (ie. A vs X, and B vs X) ? > >the (desirably) common way to do that is to read the docs first. ?dist vQ
on 06/24/2008 09:41 AM Gundala Viswanath wrote:> Hi all, > > Suppose I have 2 matrices A and B. > And I want to measure how good each of this matrix is. > > So I intend to compare A and B with another "gold standard" > matrix X. Meaning the more similar a matrix to X the better it is. > > What is the common way in R to > measure matrix similarity (ie. A vs X, and B vs X) ?If I am correctly interpreting what you are looking for see ?dist and perhaps ?hclust. RSiteSearch("matrix similarity") may also prove to be useful. HTH, Marc Schwartz
Hi Gundala,>> Suppose I have 2 matrices A and B. >> And I want to measure how good each of this matrix is.You really want to be using Robert & Escoufier's RV-coefficient (A unifying tool for linear multivariate statistical methods: The $RV$-coefficient Appl. Statist., 1976, 25, 257-265). Several packages in R use it. If I were you I would look at the coinertia() function in package ade4, which is a fine implementation, with a good plot method. There is also a randomization test. You could also look at Procrustean analysis (also with a randomization test and also implemented in the named package). HTH, Mark. Gundala Viswanath wrote:> > Hi all, > > Suppose I have 2 matrices A and B. > And I want to measure how good each of this matrix is. > > So I intend to compare A and B with another "gold standard" > matrix X. Meaning the more similar a matrix to X the better it is. > > What is the common way in R to > measure matrix similarity (ie. A vs X, and B vs X) ? > > > - Gundala Viswanath > Jakarta - Indonesia > > ______________________________________________ > 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. > >-- View this message in context: http://www.nabble.com/Measuring-Goodness-of-a-Matrix-tp18092757p18100047.html Sent from the R help mailing list archive at Nabble.com.
What do you mean by "A similar to X"? Do you mean norm of the difference, similar eigenvalues/vectors, anything else? --- On Wed, 25/6/08, Gundala Viswanath <gundalav at gmail.com> wrote:> From: Gundala Viswanath <gundalav at gmail.com> > Subject: [R] Measuring Goodness of a Matrix > To: r-help at stat.math.ethz.ch > Received: Wednesday, 25 June, 2008, 12:41 AM > Hi all, > > Suppose I have 2 matrices A and B. > And I want to measure how good each of this matrix is. > > So I intend to compare A and B with another "gold > standard" > matrix X. Meaning the more similar a matrix to X the better > it is. > > What is the common way in R to > measure matrix similarity (ie. A vs X, and B vs X) ? > > > - Gundala Viswanath > Jakarta - Indonesia > > ______________________________________________ > 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.
Thanks so much all. I will try out each of your suggestions. - Gundala Viswanath Jakarta - Indonesia On Wed, Jun 25, 2008 at 8:01 AM, Moshe Olshansky <m_olshansky at yahoo.com> wrote:> What do you mean by "A similar to X"? > Do you mean norm of the difference, similar eigenvalues/vectors, anything else? > > > --- On Wed, 25/6/08, Gundala Viswanath <gundalav at gmail.com> wrote: > >> From: Gundala Viswanath <gundalav at gmail.com> >> Subject: [R] Measuring Goodness of a Matrix >> To: r-help at stat.math.ethz.ch >> Received: Wednesday, 25 June, 2008, 12:41 AM >> Hi all, >> >> Suppose I have 2 matrices A and B. >> And I want to measure how good each of this matrix is. >> >> So I intend to compare A and B with another "gold >> standard" >> matrix X. Meaning the more similar a matrix to X the better >> it is. >> >> What is the common way in R to >> measure matrix similarity (ie. A vs X, and B vs X) ? >> >> >> - Gundala Viswanath >> Jakarta - Indonesia >> >> ______________________________________________ >> 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. >