STA 215 - Computing
Some problems will require statistical computing.
Splus
is recommended. Any other software (Gauss, Xlisp-Stat etc) is ok.
Get a free tutorial and reference on
Splus
in general (section on Splus; postscript or html).
Splus is most efficiently used from within
emacs:
-
You will need to make some changes to
your configuration file. Add the following lines to your
".emacs" file.
If you don't have a .emacs file (in your home directory), create one with
these commands in it:
- Commands for running Splus from
within emacs.
- Find a short tutorial on emacs in the Duke Statistics
computing guide -- look for the section on "Editing Files".
Some Splus examples which you can use as templates for other homework
problems:
- First examples
-
- Univariate posterior distributions
(evaluation, posterior simulation, predictive etc).
-
- Bivariate posterior distributions
(evaluation, posterior simulation, predictive etc).
- Posterior simulation in
Normal Linear Regression models.
- Hierarchical model posterior distributions
(evaluation, posterior simulation, predictive etc).
-
- copy the data set into a file "rats.data"
in your directory (either just cut and paste the rats with the mouse;
or use the pull down menu "File" in Netscape, choose "Save As")
- Gibbs sampler.
-
You can use Mathematica for symbolic computations
(derivatives, second derivative matrices etc).