similar to: MASS library rob.cov ellipse

I figured this out so I wanted to post a response to my own question. Thanks to Brian Ripley for his hint, which got me looking in the right direction. The plot I had seen before that I wanted was automatic output to the cor.plot command in the mvoutlier library. A similar tolerance ellipse can be obtained from the covPlot command in the robustbase library, using which="tolEllipsePlot"

I'm just curious . . . if effect sizes are so important, and possibly a better way of looking at results than p-values, since they don't depend on effect size (Kline,2004; Murphy and Myors, 2004), why don't any of the classical tests, like t.test or glht specified for Tukey's posthocs, return effect sizes? I say "classical" because I'm sure there may be packages out

I am a very novice R user, a social scientist (linguist) who is trying to learn to use R after being very familiar with SPSS. Please be kind! My concern: I cannot figure out a way to get an accurate count of observations of one column of data split by a factor when there are NAs in the data. I know how to use commands like tapply and summaryBy to obtain other summary statistics I am interested

I don?t know if this question properly belongs on this list, but I?ll ask it here because I?ve been using R to run linear regression models, and it is only in using R (after switching from using SPSS) that I have discovered the process of fitting a linear model. However, after reading Crowley (2002), Fox (2002), Verzani (2004), Dalgaard (2002) and of course searching the R-help archives I cannot

Wouldn't something like table(status) give you want you want? E.g.: R> status <- factor(c("A", "B", "A", NA, "A", "B")) R> table(status) status A B 3 2 Andy From: Jenifer Larson-Hall > > I am a very novice R user, a social scientist (linguist) who > is trying to learn to use R after being very familiar with >

Hi! I tested two different implementations of the robust MCD estimator: cov.mcd from the MASS package and covMcd from the rrcov package. Tests were done on the hbk dataset included in the rrcov package. Unfortunately I get quite differing results -- so the question is whether this differences are justified or an error on my side or a bug? Here is, what I did: > require(MASS) >

Hi, I would like to select the most frequent value level in a set of three variables. Three different observators have judged hair color in study subjects. Mostly they judge the same color, sometimes there is a slight difference. I want to know what most of the observators have chosen (so at least 2) from the 3 observations. E.g. If two out of three observators decide the hair is black, then

Dear list, here is something I do not understand about cov.rob. > dat <- rmvnorm(200,rep(0,10),diag(10)) > cov.rob(dat,method="mcd") > cov.rob(dat,method="mcd",quantile.used= floor(3*211/4)) # All fine; default for quantile.used is floor(211/2) > dat <- rmvnorm(20,rep(0,10),diag(10)) > cov.rob(dat,method="mcd") # quantile.used is floor(31/2).

Hi, after looking around I was not able to get info about these two questions: 1. Is there a function to have a "jackknifed corrected var/cov estimate" (as described in MacKinnon and White 1985) in a standard OLS regression? 2. Does R possess a LAD (Least Absolute Deviation) regression function? Any help? Thanks -- ======================================================== Angelo

Surprise! You've just received a greeting from "Jenifer" ([1]jenifer_brown at usa.net)! To view this greeting card, click on the following Web address at anytime within the next 30 days. [2]http://www.thebestgreetings.com/pickup7722.htm If that doesn't work, go to [3]http://www.thebestgreetings.com/pickup and copy and paste this code: 8272635YJKAH7

Dear all, I would like to conduct a Pearson's correlation using cor.test separately for each individual in my data set. Each individual has nine observations of the measurement variable 'Delta13C'. I can figure our how to do it manually one 'Individual_ID' at a time, but I cannot figure out how to automate the process (a loop I am guessing). In addition, I would like to

Hi, I am trying to plot two types of data on the same graph: points and distributions. I am attempting to use the panel.groups function, but cannot seem to get it to work. I have a melted data set and put in a FLAG column to separate my data into the two groups that I would like to plot, point data (FLAG=0) and the distribution(FLAG=1). Here is the code i am using in R: stripplot(

Do you have anything detailing what the goal of each phase in Xenrt is? Phases 4 and 5 seem to be pretty much identical. Thanks, Paul Larson _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

Dear list, The below dataset and code creates a new dataset with the results from the function cor.test being performed on each individual ('Individual_ID') from my original dataset. How do I convert each variable from the cor.test results to a numeric data type, as it is passed into the new dataframe? For example, 'estimate', 'p.value', and 'conf.int' should be

I have MySQL Cluster set up for OpenSIPS which allows for the best Redundant High-Availability. I was wondering if it's possible for Asterisk to also use multiple database servers for Realtime? Currently with Realtime I am only able to point to a single IP address for a database. If that database server goes down that Asterisk is pointed to then Asterisk won't be able to do anything.

I start my dovecot with the "-c /path/to/custom/config" option so I can run multiple instances. Been trying out 2.0.1 so I can upgrade my boxes cleanly, but I require managesieve. So after installing the latest sources of the Pigeonhole plugin, I'm getting this when trying to start dovecot: # /usr/local/sbin/dovecot -c /usr/local/etc/dovecot/dovecot_custom.conf managesieve(root):

Hi, I was trying to write a RESTful service and was planning on testing via tools such as cURL and the basic http libs. With the InvalidAuthenticityToken piece that is turned by default in Rails 2.0.2, I have to provide the token with each request. This is something of a pain for a programmable client that may not make a GET request before performing other actions, specifically POST, PUT and

I've installed the rpm's and everything seems to be set up fine. I've been through many documents (even the one on redhat that says i must change localhost to 127.0.0.1 in one of the config files (/etc/xinetd.d/swat). When i direct mozilla to http://localhost:901 I get, "The connection was refused when attempting to contact localhost:901 I think maybe that something is not

I've started working on a pure-java port of Theora under the LGPL, as a subproject of FMJ, the open-source implementation of JMF. It is similar to and dependent on the jogg/jorbis libraries from jcraft. The Cortado implementation is nice, but since it is GPL, that is too restrictive for FMJ, which is LGPL. This is, naturally, a large undertaking, and any help by anyone interested would

Hi everyone, We are looking for some data sets working with relative risk mortality. so, someone know where can I find the data.mgus dataset and the data.mgus? Using 1384 records from Minnesota. This data set are used in the : Robert A. Kyle, Terry M. Therneau, S. Vincent Rajkumar, Janice R. Offord, Dirk R. Larson, Matthew F. Plevak, and L. Joseph Melton III. A long-term study of prognosis in