similar to: How does clusplot exactly make use of cmdscale?

Hello, I have a large data set that has more columns than rows (sample data below). I am trying to perform a partitioning cluster analysis and then plot that using pca. I have tried using CLUSPLOT(), but that only allows for 'princomp' where I need 'prcomp' as I do not want to reduce my columns. Is there a way to edit the CLUSPLOT() code to use 'prcomp', please? #

Dear R folk: Perhaps I'm just dense today, but I am having trouble reproducing the principal components plotted and summarized by clusplot. Here is a brief example using the pluton dataset. clusplot reports that the first two principal components explain 99.7% of the variability. But this is not what princomp is reporting. I would greatly appreciate any advice. With best regards, -- Tom

Dear all I'm trying to run a cluster analysis with R Here are the commands: mydata <- na.omit(matrix) # listwise deletion of missing mydata <- scale(matrix) # standardize variables fit <- kmeans(mydata, 8) # 8 cluster solution # get cluster means aggregate(mydata,by=list(fit$cluster),FUN=mean) # append cluster assignment mydata <- data.frame(mydata, fit$cluster)

The following code in clusplot.default (package cluster) is in error: x1 <- cmdscale(x, k = 2, eig = TRUE) var.dec <- sum(x1$eig)/sum(diag(x1$x)) if (var.dec < 0) var.dec <- 0 if (var.dec > 1) var.dec <- 1 x1 <- x1$points x1 has components with names "points" and "eig", not "x", so

In applying multidimensional scaling, it seems to me that sometimes the underlying dimensionality of the matrix is 1. However I found a case where cmdscale failed when I tried k=1. Here it is: m<-matrix( c(.5,.81,.23,.47,.61, .19,.5,.06,.17,.28, .77,.94,.5,.74,.85, .53,.83,.26,.5,.64, .39,.72,.15,.36,.5), nrow=5) # BTW I think cmdscale uses only the lower triangle--how to enter only # that

Hello, I have a large data matrix (68x13112), each row corresponding to one observation (patients) and each column corresponding to the variables (points within an NMR spectrum). I would like to carry out some kind of clustering on these data to see how many clusters are there. I have tried the function clara() from the package cluster. If I use the matrix as is, I can perform the clara

kalish at psy.uwa.edu.au wrote: > > I'm a newbie at R, and can't get libraries to really work. > I did this: > > library(help = mva) > cancor Canonical Correlations > cmdscale Classical (Metric) Multidimensional Scaling > dist Distance Matrix Computation > hclust Hierarchical Clustering

I am a relative novice with R and am having some difficulty using 'clusplot' (package Cluster). I have performed PCA analysis (using vegan) on a large set of morphometric measurements and revealed up to 4 principal components. To examine the grouping of the data I have used PAM followed by clusplot to visualise the clusters. My problem is that I would like to see the clusters plotted on

I created a clusplot from PAM results. It represents how signals have been classified. Signals are identified by a numerical label. My trial distance matrix is made up of 10 rows, one for eacjh signal. I assigned the signals iidentifiers as rownames of the distance matrix. rwn [1] "1104" "1332" "2057" "2425" "2483" "2530"

Hi there, I want to do classify some 2-dimensional points into four clusters by pam() in the cluster package. However, I encountered some problems. 1. How can I change the "xlab" and "ylab" instead of the default "Component 1" and "Component 2"? When I put "xlab" option in the function, it always says "formal argument "xlab"

Dear R developers, there appears to be a small problem with function cmdscale: for non-Euclidean distance matrices, using option add=FALSE (the default), cmdscale misses the smallest eigenvalue. This affects GOF statistic g.1 (See Mardia, Kent + Bibby (1979): Multivariate Analysis, eq. (14.4.7). The corresponding formula in Cox + Cox (2001): Multidimensional Scaling, 2nd ed., p 38, would

Hello all, I'm using R1.7.1 on Linux, generating sammon-optimized MDS plots from distance matrices. This is a calculation I run routinely, often on sample sets of up to 100 samples. This time, with three samples, the sammon function returned an error (shown below), which I tracked down to the cmdscale function it uses to find a starting configuration. In short, cmdscale is returning NaN

The function cmdscale tries to copy names from the source to the result. This only works if the source is a matrix. If m is a matrix with labels (rownames) and d is an object of class "dist" with labels, this works: cmdscale(m) ...but with this, there are no labels in the results: cmdscale(d) However, this works: cmdscale(as.matrix(d)) My suggestion is to change, in

Hi We have a few questions regarding the use of the "isoMDS" function. When we run "isoMDS" function using 60,000 x 60,000 data matrix, we get the following error message: ------------------------------------ cmdscale(d, k) : invalid value of 'n' Calls: isoMDS -> cmdscale ------------------------------------ We checked the source code of "cmdscale" and

Full_Name: Cam Webb Version: 1.6.0 (fink X11 compile) OS: Mac OS X (Jaguar) Submission from: (NULL) (64.168.28.87) This is an unpredictable, intermittant hang during cmdscale of the mva library. Some data never cause a problem, other data always do, abut I can't track down the difference in the structure of the data. Sometimes the function will work for `difficult' data after it has

Dear Friends, require(cluster) x <- rbind(cbind(rnorm(10, 0, 0.5), rnorm(10, 0, 0.5)), cbind(rnorm(15, 5, 0.5), rnorm(15, 5, 0.5))) plot(pp <- pam(x, 2), which.plots = 1) How can I extract the coordinates used in the plot? _____________________________ Professor Michael Kubovy University of Virginia Department of Psychology Postal Address: P.O.Box 400400, Charlottesville, VA 22904-4400

I'm looking for someone to explain the difference between these procedures. The function prcomp() does principal components anaylsis, and the function cmdscale() does classical multi-dimensional scaling (also called principal coordinates analysis). My confusion stems from the fact that they give very similar results: my.d <- matrix(rnorm(50), ncol=5) rownames(my.d) <-

Hello, I have a dilemma that I'm hoping the R gurus will be able to help resolve. For background: My data is in the form of a (dis)similarity matrix created from taking the inverse of normalized reaction times. That is, each cell of the matrix represents how long it took to distinguish two stimuli from one another-- a square matrix of 45X45 where the diagonal values are all zero (since this

Hi. I know matrices that use distances between places works fine when using cmdscale. However, what about matricies such as: A B C D E A 0 1 23 12 9 B 1 0 10 12 3 C 23 10 0 23 4 D 12 12 23 0 21 E 9 3 4 21 0 i.e. matrices which do not represent physical distances between places (as they would not make sense for real distances such as the one above)

I have a dataframe like this (toy example): x y z "a" "a" 0 "a" "b" 1 "a" "c" 2 "b" "a" .9 "b" "b" 0 "b" "c" 1.3 "c" "a" 2.2 "c" "b" 1.1 "c" "c" 0 The observations are from a matrix like this: c 2.2 1.1 0.0 b 0.9 0.0