similar to: speeding up a recursive function

SAS Enterprise Miner recommendeds to standardize using X / STDEV(X) versus [X ? mean(X)] / STDEV(X) Any thoughts on this? Pros Cons Philip

SAS has something called the "cubic criterion" cutoff for finding the most appropriate number of clusters. Does R have anything that would replicate that? I've been searching the lists and can't seem to find anything that would point me in the right direction. Thank in advance, Philip Bermingham

Dear All, just a quick example: > x = 1:25 > x[12] = NA > x [1] 1 2 3 4 5 6 7 8 9 10 11 NA 13 14 15 16 17 18 19 20 21 22 23 24 25 > y = x[x<10] > y [1] 1 2 3 4 5 6 7 8 9 NA Is there any way of NOT getting NA for y = x[x<10]? Similarly > y = x[x<15] > y [1] 1 2 3 4 5 6 7 8 9 10 11 NA 13 14 How do I get rid of the NA (not post

Hi All, I am counting the number of occurrences of the terms listed in one vector in another vector. My code runs: for( i in 1:length(vector3)){ vector3[i] = sum(1*is.element(vector2, vector1[i])) } where vector1 = vector containing the terms whose occurrences I want to count vector2 = made up of a number of repetitions of all the elements of vector1 vector3 = a vector of NAs that is

Hi All, is there a way of predicting memory usage? I need to build an array of 86000 by 2500 numbers (or I might create a list of 2 by 2500 arrays 43000 long). How much memory should I expect to use/need? Cheers, Fede -- Federico C. F. Calboli Department of Epidemiology and Public Health Imperial College, St. Mary's Campus Norfolk Place, London W2 1PG Tel +44 (0)20 75941602 Fax +44

Dear All, I will soon be working with NIH and possibly FDA. Will I be able to use R or will I be forced to use SAS? Cheers, Federico -- Federico C. F. Calboli Department of Epidemiology and Public Health Imperial College, St. Mary's Campus Norfolk Place, London W2 1PG Tel +44 (0)20 75941602 Fax +44 (0)20 75943193 f.calboli [.a.t] imperial.ac.uk f.calboli [.a.t] gmail.com

HI All, I have written and succesfully uploaded a new package. The licence it is under is 'GPL' --no version. My assumption is, since all the code is written in R the licence R used for R would affect the code (hence my "GPL" stands for "whatever version of the GPL R is under") I am happy with the licencing I used, but I'd like to ask if there is any transitive

Hi All, I have some data where the dependent variable is a score, low (1:3) or high (8:9), and the independent variables are 21 genotypic markers. I'm fitting a logistic regression on the whole dataset after transforming the score to 0/1 and normal linear regression on the high and low subsets. I all cases I have a numer of cases of data 'duplications', i.e. different

Hi All, I would like to output the results of a function into a text file, legible as a such. The function produces a summary quite like: summary(lm(x ~ y + w * z)) [for instance] and I am not clear how to save this summary into a text file 'automagically', because I need to be able to do it in a for() loop. Cheers, Federico -- Federico C. F. Calboli Department of Epidemiology

Hi All, I'm having a problem with barplot: mydata [1,] 2 108 0 0 0 1 3 0 0 0 0 0 7 18 3 4 8 20 26 20 19 7 1 1 mycol = c(rep('yellow', 2), rep('white', 3), rep('orange',2), rep('white', 5), rep('orange',3), rep('red',9)) barplot(mydata, col = mycol) gives me an uniformly yellow barplot. How do I solve this? bw Federico

Hello all, a friend has a problem with tiff() which I was unable to help about. I searched the error messages to no avail. When he tries: tiff(filename = "FedeWhyDoesntThisBloodyWork.tif", width = 5, height = 5, units = "cm", bg = "white", res = 1200) Error in tiff(filename = "FedeWhyDoesntThisBloodyWork.tif", width = 5, : unable to start device

Hi All, I would like to know, is there a *ballpark* figure for how many parameters the minimisation routines can cope with? I'm asking because I was asked if I knew. Cheers, Federico -- Federico C. F. Calboli Department of Epidemiology and Public Health Imperial College, St. Mary's Campus Norfolk Place, London W2 1PG Tel +44 (0)20 75941602 Fax +44 (0)20 75943193 f.calboli [.a.t]

Hi All, I have a data frame where a couple of columns are factors, with long and complex names. Everything works ok --in R, but I need to export the data so it can be used on a dumber program (one with a three letters name starting with S...). I know that those complex factor names are causing problems reading the data in from acsv file, so I was thinking of renaming the factors. Problem is, I

Hi All, I am writing a function that reads a file in myfile = file('myfile.raw', 'rb') . . . . . close(myfile) No matter what, I get the warning Warning message: closing unused connection 3 (myfile.raw) Since the whole thing is in a function, I'd like to avoid unecessary noise for the user, and I'd like to kill the warning -- without having to mess with global options.

Hi All, does anyone ever import old SPSS files in a sl3 format? read.spss('file.sl3') does not seem to work... it's not recognised as a supported SPSS format at all. Best, Fede -- Federico C. F. Calboli Department of Epidemiology and Public Health Imperial College, St. Mary's Campus Norfolk Place, London W2 1PG Tel +44 (0)20 75941602 Fax +44 (0)20 75943193 f.calboli

Hi All, is there a reasonably simple way of using a black and white chequer/checker board pattern as a colour: barplot(mydata, col = c('red', 'blue' 'checkerboard')) ? BW F -- Federico C. F. Calboli Neuroepidemiology and Ageing Research Imperial College, St. Mary's Campus Norfolk Place, London W2 1PG Tel +44 (0)20 75941602 Fax +44 (0)20 75943193 f.calboli

Hi everyone, I'm running a cox ph model on a dataset with a number of variables. Each variable has a different number of missing data, so that coxph() drops the individuals who are missing data at one or more variables. Because of this dropping (totally fine btw) I want to know how many events I am left with in the model. Is there a way of extracting them from the coxph() fit? or in any other

Hi, I am subsetting a matrix thus: test [,1] [,2] [,3] [1,] 1 7 13 [2,] 2 8 14 [3,] 3 9 15 [4,] 4 10 16 [5,] 5 11 17 [6,] 6 12 18 test[cbind(c(1,3,5), c(2,1,3))] [1] 7 3 17 This works fine, and is the equivalent of c(test[1,2], test[3,1], test[5,3]). cbind(c(1,3,5), c(2,1,3)) would obviously look like: [,1] [,2] [1,] 1 2 [2,]

Hi All, is there a way of using strsplit with a forward slash '/' as the splitting point? For data such as: 1 T/T C/C 16/33 2 T/T C/C 33/36 3 T/T C/C 16/34 4 T/T C/C 16/31 5 C/C C/C 28/29 6 T/T C/C 16/34 strsplit(my.data[1,1], "/") # and any variation thereof Error in strsplit(apoe[1, 1], "/") : non-character

Hi All, can I have a plot where the symbol for the dots is smaller than pch =20 but bigger than pch = '.'? Best, Fede -- Federico C. F. Calboli Department of Epidemiology and Public Health Imperial College, St. Mary's Campus Norfolk Place, London W2 1PG Tel +44 (0)20 75941602 Fax +44 (0)20 75943193 f.calboli [.a.t] imperial.ac.uk f.calboli [.a.t] gmail.com