Linux partition guid

Here is a short but useful guide showing how to partition a hard drive for a new Linux installation.

Configuring AUCTeX

This post explains how to configure AUCTeX to use different PDF file viewers.

Ra vs. compiler package

R seems to have two byte code compilers: the Ra add-on module (and the accompanying "jit" package) and the "compiler" package came with the default installation. I wonder how they differentiate from each other and what the strengths and weaknesses of each are.

CppBugs

A simple way to get CppBugs to work is to copy the "cppbugs" folder to "/usr/local/include". On my Ubuntu 10.04 system, I also need to modify the make file located in the test file directory and replace the "ARMADILLO_LIBS = llapack" with "ARMADILLO_LIBS = -larmadillo".

As a BUGS/JAGS user, I think this project is very promising and extremely interesting. It will be even more attractive if CppBugs can be integrated with R (maybe through Rcpp) in the similar way that R2WinBUGS integrates WinBUGS with R.

Using Rcpp for faster MCMC simulation

Here is a very informative blog post showing how to use Rcpp to speed up MCMC simulation.

OpenGeoDa, again

Another new release of OpenGeoDa is out, but the same problems persists: while the Linux version opened .shp files with Chinese names without problems, the windows version crashed.

Now the new version also works on Ubuntu 11.04 64-bit.

The "rube" package

The "rube" package is very promising. It builds upon the "R2WinBUGS" package and adds some very useful features. I hope it further extends to the JAGS engine because JAGS is apparently the future of the BUGS famine.

R for programmer

This is a useful document.

WebOS is gone

So that's it, HP has decided to ditch its short-lived tablet, smartphone etc.

Ibus mode

Ibus mode for Emacs allows the use of Ibus input method in Emacs. Very convenient.

13 greatest error messages of all time

Here is a fun post.

Tango color theme for Emacs

I like the Tango color theme for Emacs

Get predicted values from GAM models

I used to rely on the default plot produced  by the GAM command; now I realized that it is quite simple to produce and plot predicted predicted values using the "predict.gam()" function in the "mcgv" package.

Interaction effect plot

I am glad to find out that the "effects" package can now handle mixed effect model results from "lme4".