similar to: help with cluster stopping rules

Has anyone implemented Tibrishani's gap statistic in R or S plus? If so I would greatly appreciate the relevant script file. Any help will be much appreciated Kind regards Dr Graham Leask Economics and Strategy Group Aston Business School Aston University Aston Triangle Birmingham B4 7ET Tel: Direct line 0121 204 3150 email g.leask@aston.ac.uk [[alternative HTML version deleted]]

Dear List Has anyone used R to distnguish between alternative forecasting models? In particular is the Diebold Mariano test available for use within R. Any assistance would be greatly appreciated. Graham Leask Lecturer in Strategy Economics & Strategy Group Aston University Aston Triangle Birmingham B4 7ET Tel: 0121 204 3150 E Mail: g.leask at aston.ac.uk

Dear List I am looking for a script that will calculate the Box M test to test the homogeneity of the variance/covariance matrix between two matrices. If anyone could send me the script I would appreciate it. I am aware of the scepticism about this test, where due to extreme sensitivity a p value of 0.01 is recommended. Despite this however Box's M test is the established

I have a set of data that consists of a number of biological measurements. The columns are Time that runs from 01/01/2005 to 01/5/2007, Group which has 23 levels and postcode which is nested within group. This is a balanced panel but the number of postcodes differs within groups, from 15 to 400. The rest of this data consists of a number of columns of quantitative measures, largely counts.

I have two data frames with a number of common variables that I wish to put into "long format". The first contains the variables es(Csales) [1] "terr" "Dec.02" "Jan.03" "Feb.03" "Mar.03" "Apr.03" "May.03" "Jun.03" [9] "Jul.03" "Aug.03" "Sep.03" "Oct.03"

Does any package available in R contain the V-fold cross-validation method for determining the right number of clusters? Any help greatly appreciated Kind regards Dr Graham Leask Economics and Strategy Group Aston Business School Aston University Aston Triangle Birmingham B4 7ET Tel: Direct line 0121 204 3150 email g.leask@aston.ac.uk [[alternative HTML version deleted]]

Which files are needed to build clang? Is it clang-3.0rc2 and llvm-3.0rc3 or do I need the whole test suite? John Dr John P. Fletcher Tel: (44) 121 204 3389 (direct line), FAX: (44) 121 204 3678 Chemical Engineering and Applied Chemistry (CEAC), Associate Dean - External Relations, School of Engineering and Applied Science (EAS), Aston University, Aston Triangle, BIRMINGHAM B4 7ET 

Removing rows with NAs, using na.omit(), doesn't seem to be working for me. Dataset: > str ( ex10s ) 'data.frame': 2189576 obs. of 5 variables: $ LOPNR : int 58 58 58 58 64 64 64 64 64 64 ... $ DIAGNOS: Factor w/ 173 levels "F20","F200","F2000",..: 128 128 128 128 105 105 105 160 105 105 ... $ X_DATE : int 20060821 20061207 20080102 20090904

Thanks. I was "believing" an Excel import of the file - as you say, a re-import into R still has 333 columns. I shall look elsewhere for the cause of the mysterious truncation. Stuart > ----- Original Message ----- > From: "Thomas Lumley" <tlumley at u.washington.edu> > To: "Stuart Leask" <stuart.leask at nottingham.ac.uk> > Cc:

Hello, I have been using the "cophenetic" function for objects of class "dendrogram" and I have realised that it gives different results when it is used with objects of class "hclust". For instance, running the first example in the help file of the "cophenetic" function, d1 <- dist(USArrests) hc <- hclust(d1, "ave") d2 <-

Note that cophenetic.default (which works on the output of hclust(dist(X))) uses the row names of X as labels. as.dendrogram.hclust does not retain those row names so cophenetic.dendrogram cannot use them (so it orders them based on the topology of the dendrogram). Bill Dunlap TIBCO Software wdunlap tibco.com On Thu, Apr 21, 2016 at 7:59 AM, William Dunlap <wdunlap at tibco.com> wrote:

Hi Stuart, I often use this small function standardize <- function(x) ( x - mean(x, na.rm=T) ) / sqrt(var(x, na.rm=T)) to standardize variables. You should be able to use this to do what you want by splitting the data frame into sections based on the factor level, using standardize() to create a new variable in each section, then paste the data frame back together. Something like: #

Hello, I've been trying to figure out how to access the individual elements from an object of class phylo. I am reading in 201 trees created by paup as below. > read.nexus("A_30knj_200t.txt", tree.names= NULL) -> anj30 > anj30[1] $tree1 $edge [,1] [,2] [1,] "-1" "-2" [2,] "-2" "-3" [3,] "-3" "1"

Dear List members I have a large dataset organised in choice groups see sample below +-------------------------------------------------------------------------------------------------+ | dn obs choice acid br date cdate situat~n mth year set |

On Nov 7, 2011, at 2:00 PM, Bill Wendling wrote: > Good day, LLVMers! > > We are starting on our third (and hopefully last) round of testing for LLVM 3.0. Please visit: > > http://llvm.org/pre-releases/3.0/rc3/ > > for the sources. There are also binaries for Darwin up there, with more to come during the week. Please build this release candidate, test it out on your

Dear List I am trying to fit a multinomial model using the mlogit package. Attempting to load the data into mlogit presents the following error. MLOG<-mlogit.data(Mult3,shape="long",choice="CHOICE",alt.var="mode.ids",indivs = "set3",chid.var = "obs") Error in `row.names<-.data.frame`(`*tmp*`, value = c("1.1", "1.2",

Hello, I analyse some free-sorting data so I use hierarchical clustering. I want to compare my proximity matrix with the tree representation to evalute the fitting. (stress, cophenetic correlation (pearson's correlation)...) "The cophenetic similarity of two objects a and b is defined as the similarity level at wich objects a and b become members of the same cluster during the course of

Dear List How do you change the colour settings for the banner/silhouette plot? I am trying to produce a black and white plot of publication quality. Is there a way to set black and white plots as the default for R graphics? Any help greatly appreciated. Graham Leask Economics & Strategy Group Aston University [[alternative HTML version deleted]]

(Many thanks to David Barron & Jonathan Baron for pointing me to 'recode' in the 'car' package). I think I've been told this before, but how do I search for a function/keyword in libraries I don't yet have installed? (ie. on the CRAN site I tried the search engines with "recode" etc., but didn't pick up the car package this way) Stuart Dr Stuart Leask

Dear All, I wrote a function for cluster analysis to compute cophenetic correlations between dissimilarity matrices (using the VEGAN library) and cluster analyses of every possible clustering algorithm (SEE ATTACHED) http://old.nabble.com/file/p26288610/cor.coef.R cor.coef.R . As it is now, it is extremely long, and for the future I was hoping to find a more efficient way of doing this sort of