search for: mbmiller

Is there an R function for computing a variance-covariance matrix that guarantees that it will have no negative eigenvalues? In my case, there is a *lot* of missing data, especially for a subset of variables. I think my tactic will be to compute cor(x, use="pairwise.complete.obs") and then pre- and post-multiply by a diagonal matrix of standard deviations that were computed based

...t isn't quite it because I tried it and it didn't work! Any advice greatly appreciated. Thanks in advance. Mike -- Michael B. Miller, Ph.D. Assistant Professor Division of Epidemiology and Community Health and Institute of Human Genetics University of Minnesota http://taxa.epi.umn.edu/~mbmiller/

I connected from my desktop Linux box to a Linux server using ssh in an xterm, but that xterm was running in Xvnc. I'm running R on the server in that xterm (over ssh). Something went wrong with Xvnc that has caused it to hang, probably this bug: https://bugs.launchpad.net/ubuntu/+source/vnc4/+bug/819473 So I can't get back to that ssh session or to R. I had done a bunch of work

Importing data with a header row using read.delim, one variable should be named @5HTT but it is automatically renamed to X.5HTT, presumably because the "@" is either unacceptable or misunderstood. I've tried to find out what the rules are on variable names but have been unsuccessful. I'll bet someone here can tell me where to look. Maybe it's hidden away in here

Hi there, Suppose mu is constant, and error is normally distributed with mean 0 and fixed variance s. I need to find a statistics that: Y_i = mu + beta1* I1_i beta2*I2_i + beta3*I1_i*I2_i + +error, where I_i is 1 Y_i is from group A, and 0 if Y_i is from group B. It is large when beta1=beta2=0 It is small when beta1 and/or beta2 is not equal to 0 How can I find it by R? Thank you very much

The R "cut" command is entirely different from the UNIX "cut" command. The latter retains selected fields in a line of text. I can do that kind of manipulation using sub() or gsub(), but it is tedious. I assume there is an R function that will do this, but I don't know its name. Can you tell me? I'm also guessing that there is a web page somewhere that will tell

Nano is Free Software and a nice intro text editor. It also starts up very quickly and has good syntax highlighting functionality, so it makes a nice file viewer. The syntax highlighting is configured in the ~/.nanorc file. See the attached code and screenshot. I was looking for good nano syntax highlighting code for R when I found by Stephen Haptonstahl's code here:

I make plenty of scatterplots, especially using scatterplot.matrix from library(car). One thing I don't know how to do is determine which points are plotted last. Sometimes I plot a large number of points for multiple groups represented by different colors. I would like to guarantee that point that are far from the centroid for their group are plotted last. This way they will be

I sometimes get errors of this form: Error: cannot allocate vector of size 13.8 Gb I've also seen "Gb" used in R documents. Is "Gb" being used to refer to gigabyte? We usually refer to bytes and gigabytes when discussing memory usage, but the lowercase "b" more often refers to bits. According to Wikipedia: http://en.wikipedia.org/wiki/Gigabyte

I'm getting the impression from on-line docs that R cannot work with single-precision floating-point numbers, but that it has a pseudo-mode for single precision for communication with external programs. I don't mind that R is using doubles internally, but what about storage? If all I need to store is single-precision (32-bit), can I do that? When it is read back into R it can be

First, it looks like there is bug in the documentation... According to the documentation for system(): http://stat.ethz.ch/R-manual/R-patched/library/base/html/system.html input if a character vector is supplied, this is copied one string per line to a temporary file, and the standard input of command is redirected to the file This seems to mean that the standard input

I am printing numbers onto horizontal bars in a bar plots, but I am finding it difficult to make the number always the right size. If there are more bars, the bars get narrower and the font is too big. I also find that if I change the size of the graph, the bars will get wider or narrower and the font stays about the same size. The result depends on whether I view the graph in X11 or in

I note that "current implementations of R use 32-bit integers for integer vectors," but I am working with large arrays that contain integers from 0 to 3, so they could be stored as unsigned 8-bit integers. Can R do this? (FYI -- This is for storing minor-allele counts for genetic studies. There are 0, 1 or 2 minor alleles and 3 would represent missing.) It is theoretically possible

Suppose X and Y are two data frames with the same structures, variable names and dimensions but with different data and different patterns of missing. I want to replace missing values in Y with corresponding values from X. I'll construct a simple two-by-two case: > X <- as.data.frame(matrix(c("a","b",1,2),2,2), stringsAsFactors=FALSE) > X[,2] <-