similar to: Multilevel models with binary data

I've been using the nlme library to construct lme models and I'd like to extract an r-sq value for the model - how do I do this? With glm I just used the reported (null deviance-deviance)/(null deviance). Deviance is not reported directly for lme nor can it be extracted using the deviance() function. How do I work out the deviance or can I work out R-sq in some other way? Thanks, Yvonne

I'm not sure if this is a bug, or if I'm doing something wrong. =20 =46rom the worms dataframe, which is at in a file called worms.txt at =20 http://www.imperial.ac.uk/bio/research/crawley/therbook <http://www.imperial.ac.uk/bio/research/mjcraw/therbook/index.htm>=20 =20 the idea is to extract a subset of the rows, sorted in declining order of worm density, with only the maximum

Hi, I'm trying to get to grips with accessing my postgresql tables in R using RODBC. I have Mac OS 10.2.8 (Darwin 6.8) installed and R 1.8.0 installed from source and I have updated RODBC to 1.0-4. On the ODBC manager end, I am using OpenLink software's iODBC Administrator and I've set up a User DSN called "PostGRES" - odbctest suggests that this is functioning: >

Hi, I can't get R-1.7.0 to compile on my Mac. Can someone give me some pointers? The machine is an 800MHz iBook running OS 10.2.6. I have installed the December 2002 Developers Tools and have installed g77, f2c and dlcompat via fink. I've checked the versions of g77 and gcc and they're both based on gcc version 3.1. I've got Apple's X11 (Beta 3). I've added /sw/bin

Hi, I have a small simple data frame (attached) - to compare diversity of insects encountered in disturbed and unditurbed site. What i have is the count of insects - the total number of times they were encountered over 30 monitoring slots. Can someone please check for me to make sure how the 'community data matrix' for the diversity function needs to be oriented so that i'm

Hello I've got a question about list indexing. If anyone can help or point in the direction of some documentation, that'd be great. I've checked the Introduction to R and R language definition. Say you have a list of vectors: >

In a Box and Whisker plot, I thought that when there are outliers both abov= e and below the whiskers, then the whiskers should both be the same length = (plus or minus 1.5 times the inter-quartile range). If you look at the plot for SilwoodWeather on p.155 of The R Book you will = see that for November (month =3D 11) the upper whisker is shorter than the = lower, while for other months with

Hi, I can't get my head around this - can someone give me a pointer: I have a vector of values ('orig') representing areas and I want to calculate the amount contributed by each original vector values in a new vector ('new'). I find this hard to explain so here is a graphical explanation: # CODE START orig <- 10:1 #10 values with varying area new <-

In this real example (below), all four of the replicates in one treatment combination had zero failures, and this produced a very high standard error in the summary.lm. =20 Just adding one failure to one of the replicates produced a well-behaved standard error. =20 I don't know if this is a bug, but it is certainly hard for users to understand. =20 I would value your comments=20 =20 Thanks =20

Hello I'm a population ecologist and use R for all my stats and modelling. Recently I have been using R to numerically solve integral projection models. This involves constructing several large matrices. The current code by Easterling (Size-specific sensitivity: Applying a new structured population model. Ecology, 2000, 81, 694-708) uses nested loops to construct the matrices. To speed up the

Dear list, I would like to create a time series plot in which the paths of several individuals are stacked above each other, with the x-axis being the total observation period of three years ( 1.1.2004 to 31.12.2007) and the y-axis being some defined range[min,max]. My data consist of Date/Time information and the paths of 45 individual as the distance from the location of release. An example

I'm using NT 4, service pack 3, and running rjune.exe, dated 23/9/98. This works fine when I'm logged in as administrator, but when a user logs in, R fails with the message 'memory problem'. I assume that R needs (write?) access to something to which our user accounts don't normally have access. I tried giving the account full access to the R directory tree but that

> Hi there. > > > I'm trying to install samba 2.2.5 from source on solaris 2.5 sparc. It > compiles with no problems, and smbd + nmbd will run, and shares are > accessible. However, when I try to use smbpasswd to join the domain the > following occurs: > > smbpasswd -D 5 -j simpsons -r krusty -U administrator%myadminpasswordhere > > > provides the

Hi there.. I'm trying to install samba 2.2.5 from source on solaris 2.5 sparc. It compiles with no problems, and smbd + nmbd will run, and shares are accessible. However, when I try to use smbpasswd to join the domain the following occurs: smbpasswd -D 5 -j simpsons -r krusty -U administrator%myadminpasswordhere provides the following debug info: Initialising global parameters

I have a RedHat 9 installation running XFS. Cups 1.1.17-13 is installed I have compiled and installed Samba 2.2.8a and everything appears to be working apart from a minor printing problem. After I have installed a printer on my Win2K workstation I can print via samba to the cups printer using the windows PCL print driver and it works fine. However the printer status is always 'Access denied,

Greetings- I'm working with data that are multilevel in nature and have a dichotomous outcome variable (presence or absence of an attribute). As far as I can tell from reading archives of the R and S lists, as well as Pinheiro and Bates and Venables and Ripley, - nlme does not have the facility to do what amounts to a mixed-effects logistic regression. - The canonical alternative is

Hi, I am working with a multiple-item questionnaire. I have previously done item-level multiple imputation using MICE in R and right now I am attempting duplicate-scale imputation based on the guidelines listed in Enders's applied missing data analysis book. I use MICE to do MI as it allows me to specify school effect as I am working with multilevel data; my respondents come from different

Dear list,   I am looking for an R-only implementation of a Nelder-Mead process that can find local maxima of a spatially distributed variable, e.g. height, on a spatial grid, and outputs the coordinates of the new point during each evaluation. I have found two previous threads about this topic, and was wondering if something similar has been implemented since those messages were posted.   Thank

Hello, can anyone explain the following error I get when trying to use the CHECK command to check a new version of my pakcage under 1.4.0? ****** ./R CMD check ~/GLMMGibbs.0.5.1/GLMMGibbs * checking for working latex ... OK * using log directory `/homef/jonm/R-1.4.0/bin/GLMMGibbs.Rcheck' ... <Installs library, documentation, and then performs various tests, including the example,

I getting compilation errors when trying to install GLMMGibbs (see below). I'm running R v 1.7.1 on SuSE Linux 8.2. Has anyone else had this problem? I tried it on a Win2000/R 1.5.1 combination and it worked fine. Any hints are greatly appreciated. Thank you in advance, Damien >install.packages("GLMMGibbs") trying URL `http://cran.r-project.org/src/contrib/PACKAGES'