similar to: Construction of a "mean" contengency table

Hello all, I have some trouble in reconstructing a valid expression within a function, here is my question. I am building a function : SUB<-function(DF,subset=TRUE) { #where DF is a data frame, with Var1, Var2, Fact1, Fact2, Fact3 #and subset would be an expression, eg. Fact3 == 1 #in a first time I want to build a subset from DF #I managed to, with an expression like eg. DF$Fact3, # but I

The message for aov1 was "Estimated effects <may> be unbalanced". The effects are not unbalanced. The design is 'orthogonal'. The problem is that there are not enough degrees of freedom to estimate all those error terms. If you change the model to: aov1 <- aov(RT~fact1*fact2*fact3+Error(sub/(fact1+fact2+fact3)),data=myData) or to aov2 <-

I am trying to construct a two-way table where, instead of printing the two-way frequencies in the table, I would like to print the values of a third variable that correspond to the frequencies. For example, the following is easily constructed in R > fact1 <- factor(sample(LETTERS[1:3],10,replace=TRUE)) > fact2 <- factor(sample(LETTERS[25:26],10,replace=TRUE)) > fact3

I tried to run Soulseek under Wine and it starts up, gives me a message about "This application is requesting an ActiveX browser object but the Mozilla Active X control is currently noot installed. Do you wish to download and install it?". Whether I say yes or no, it proceeds into the gui of the program, but the screen does not update, no menu action, etc. Has anyone ran soulseek

Hi there, A customer of me still uses Samba 2.0.2 and it did work until know. At the moment we are not able to stop the smbd processes and it is very hard to gain access to the samba shares (only one user managed) even when we do a "kill -9 " (noot recommended) the smbd processes are available. Does anybody have an idea how to solve this ? Met vriendelijke groet, Laurens Wagemakers

Hi! Would anyone know how to generate a list of variable names from a data frame by the class of the variable? I have large tables with different numbers of columns and am trying to script some rote analyses. There are several categorizing variables (factors) and many response variables (integers and numeric). I want to extract a list of classifier column names in one list and response variable

My departmental file server is on RHL6.2(i386) (Samba 2.0.6) and participates in the company's NT domain. If an NT user wants to see shares on this UNIX(Linux) box I have only to create a UNIX account for them where the UNIX username matches the NT username. I have a Solaris 8 box (Samba 2.2.2), I cannot figure out how to make it act the same way. I have looked at winbindd but that does noot

running 3.4.5 on Solaris 10 sparc platform. Seeing odd behavior when I'm watching my smbd process through truss. When ever I just onen my Windows explorer window that just shows my mapped shares, the truss shows that the smbd process is trying to stat everything under /net. What is it doing that when I have no paths to /net specified in my smb.conf file? And is there anyway to stop

All, Looking for some help here. Not finding anything on the net that looks the same as what I'm seeing. Running Solaris 10 Sparc, on a Sunfire 5220, 16Gb of RAM. Samba version 3.4.5 and using ZFS file systems with user quotas. All cifs clients shares to this server freeze after about 10 to 15 minutes of connectivity. Only fix is to restart samba. I'm not getting any errors

In my undertstanding of the problem, the model lme1 <- lme(resp~fact1*fact2, random=~1|subj) should be ok, providing that variances are homogenous both between & within subjects. The function will sort out which factors & interactions are to be compared within subjects, & which between subjects. The problem with df's arises (for lme() in nlme, but not in lme4), when

Dear ExpeRts, Suppose I have a typical psychological experiment that is a within-subjects design with multiple crossed variables and a continuous response variable. Subjects are considered a random effect. So I could model > aov1 <- aov(resp~fact1*fact2+Error(subj/(fact1*fact2)) However, this only holds for orthogonal designs with equal numbers of observation and no missing values.

Hi all, i have a setup with chatrooms, several MeetMe conferences wich users can change inbetween. 10 users maximum in each room. It seems like when i have more than 40-45 users on the system at the same time asterisk drops abt 20 and continnues buisness as usual. Is there anyone else who have run inte this problem? Any solutions? It would me neat to hear about peoples experiences with MeetMe,

Dear all, (Sorry if the question has already been answered.) Could someone please suggest a good text editor for writing R sources ? (I know emacs exists ... but I find it a bit heavy). I use crimson (http://www.crimsoneditor.com) which is small and simple, but the R syntax seems not to be supported. Thanks for any advice

Skipped content of type multipart/signed-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-keys Size: 1759 bytes Desc: Clave PGP =?us-ascii?b?cMO6YmxpY2E=?= Url : http://oss.oracle.com/pipermail/ocfs2-users/attachments/20070214/fc85b2b9/attachment-0001.bin

I was wondering if someone can give me some assistance in approaching this issue: First, the background: I have an app that i originally did in PHP that I''m redoing in Rails. It can be used by multiple clients that have no relation to each other. The client information is in a database and is determined by the hostname. Clients then have several users related by client_id. The

Hi there, I''ve got a table construction like this: presentation contactstate Hilton new Mc Donalds emailed etc. called visited etc. Now i''ve created an join table presentationcontactstate with extra fields like comment and date time. so i know for example when i called a specific presentation. Now

hi all - i'm trying to 'R CMD build' a package, but i have what appears to be a bootstrapping problem: i've included a vignette in my package, with R code interwoven (and built using Sweave), but in this documentation i have a code line: > library(MyPackage) now, when trying to build a .tar.gz install-able version of my package in a clean state, i remove the original

Hello (Heinrich), I did not know I could do this. It doesn't seem to be documented anywhere. Thought this would be helpful to the fraction of the community using package R.oo. Note the call of a setMethodS3 method, xOne, in the setConstructorS3. This is extremely useful if xOne (in this case) is a very complex method (that you always want to be called every time you create a new object). If I

Question: When survfit() function is used upon a coxph object, the 'n' returned is vastly smaller (n=6) than the number of distinct loans in the dataset used. I am trying to estimate a Cox proportional hazards model for a set of loans (over 6000) using using time varying covariates. For this 6000+ loans, I have some 62,000 different vectors representing the loans at different periods of

Hi Im attempting to build a sample variogram for 300 obersvations of longitudinal data. So what I need to do is compute the half squared differences between pairs of residuals (for instance if a subject has 4 obersvations, this is 4 choose 2 paird differences) for each subject. Also, then I need the corresponding time differences within each individual. So the end result will be a 300 by 2