is the most widely used statistical package in biostatistics. PC version can
be accessed on Microlab computers and Unix version on ``hsph''. Students/faculty
can obtain the PC version of SAS for an annual fee of about $120. Call 617-496-SITE
for Harvard University Information Systems.
software was developed by Statistical Sciences and it is available on hsph
and in the Microlab. Splus is a superset of S, developed by folks at Bell
Labs to meet their statistical needs. It advocates and supports the use of
Exploratory Data Analysis (EDA) and encourages the user to look at their data
through sophisticated data display and plotting capabilities. It also supports
standard descriptive and predictive statistics. "Modern Applied Statistics
with Splus" (MASS) by Venables and Ripley is an excellent text covering most
of anybody would ever want to know about Splus.
is a language and environment for statistical computing and graphics. It is
a GNU project which is similar to the S language and environment. R can be
considered as a different implementation of S. There are some important differences,
but much code written for S runs unaltered under R. R provides a wide variety
of statistical (linear and nonlinear modelling, classical statistical tests,
time-series analysis, classification, clustering, ...) and graphical techniques,
and is highly extensible. On hsph, R (version 1.8.1) can be run using command
R. R is also available for free download at R.
The most current Windows version (version 2.6.0) is available on all lab machines
in room 414.
- "stata" is available on "hsph". Documentation
is available in the computing lab. The HSPH ICF office (Rm LL19) sells Stata
to students for Mac and PC/Windows.
All mathematical programs mentioned below (Matlab, Mathematica and
Maple) are available for download from the FAS
download page. You will need your student ID number in order to obtain the software.
is a numerical math program. Its development started in 1984 with mainly technical
aims. Currently, it is one of the most widely used scientific programs. There
is a very good archive
of Matlab routines. Matlab documentation and several other books are available
in the biostats computing lab.
handles complex symbolic calculations that often involve hundreds of thousands
or millions of terms. It can solve equations, differential equations, and
minimization problems numerically or symbolically. Mathematica is also doing
numerical modeling and simulations. Wolfram supports an archive.
Mathematica documentation and several other books are available in the biostats
features include a comprehensive suite of mathematical solvers, mathematical
visualization, and a rich document-processing environment. Maple supports
with applications and packages. Maple documentation and several other books
are available in the biostats computing lab.
3 Text editors
and XEmacs are
highly customizable open source text editors. XEmacs runs on Linux/Unix and
- Vi is mode-based (Tutorial)
It has a straightforward but non-mnemonic command set, and it is not fully
configurable (i.e. you can't make vi look like emacs). VIM
(VI IMproved) is a Vi clone. VIM can operate in a text based environment but
there is a version known as gVim which operates in a GUI environment.
- For new users who are unfamiliar with either
"vi/gvim" or "emacs/Xemacs", we recommend that they learn "XEmacs", if only
because it features a built-in online tutorial and extensive help.
- Also available on the public machines is WinEdt,
which an editor and shell for MS Windows. WinEdt is often used as a front-end
for TeX. On the public machines, it is used in conjunction with MikTeX.
4 Formatting packages
The main system for text formatting is LATEX
(recommended). Users considering using LATEX
should get their hands on the LATEX
Users Guide, by Les Lamport or any other good LATEX
book (check the computing lab). There is also a growing guide called The
Not So Short Introduction to LATEX
These documents lay out how to run these formatters and previewers that are
supported. Currently installed commands on hsph are:
latex - command to format documents into dvi format
pdflatex - command to format documents into pdf format
bibtex - bibliography support
dvips - dvi to postscript (printing)
ppower4 - PowerPoint-like presentations
xdvi - dvi previewer
There is more information (with examples) on the main Computing
webpage. With increasing popularity of PC-Windows machines many students use
Windows-versions of LATEX. One
of the most popular implementations is MikTeX.
5 Programming languages
- C compilers
The biostatistics department currently supports the standard c compiler
on all machines ("cc") as well as "gcc" (GNU cc). "gcc" is ansi-compliant
and the stock compilers ("cc") generally aren't.
This page is maintained by The
Last updated: 11-13-2007