statistics, data analysis and related things from Alan Dix

here now

statistics tutorial
including online notes (PDF and HTML) and 7 common errors in statistics

annotated statistics bibliography
originally to support the above
includes description of criteria to apply to books not on list

AI and intelligent interfaces:
appropriate intelligence
eco-algorithms / artificial ecologies,
the Monte-Carlo baseline

web forms and scripting
web form - learn how to use web forms and install simple web email response forms on your own site
server side scripting using php - basic tutorial
php syntax check - web-based syntax checker for your PHP scripts
obfuscate email - utility to hide email addresses in html pages
life counter - a counter for your web site counting the seconds since your birth ... or from some other time such as your PhD, first kiss, ...
colour picker - choose web colours or add a colour picker to your web application.

'intelligent' database query - you say what you want, QbB writes the query!
read about the theory in various articles about QbB (some online)
try it out online or download code for web (php/mysql/Unix) or Macintosh demonstrator

online demonstrations of 'randomness'
watch the rain fall in Gheisra
can you tell what is random and what is not?
try two-horse races with virtual coins
coin tossing experiments (which you can do with real coins too)
what would you expect from fair coins?
adjust the fairness of the online coins and see what happens
and more coin tossing experiments
you don't see the coins line up on this page, but can look at the results of multiple coin tossing experiments
download a HyperCard demo (stuffed binhex)
versions of rainfall in Gheisra and coin tossing for those sensible enough to have Macintosh computers

visualising results
see how dancing histograms bring data alive
also read about the principles behind this in my visualisation papers

Kohonen networks
self-organising neural networks (form of clustering algorithm)
documentation and download of C source code and examples

some other statistics and data mining sites
visit the World-Wide Web Virtual Library pages on statistics
Mathematics pages on statistics and probability
Dartmouth College quantitative literacy course Chance: news, materials and links to other resources and online texts
Southampton Institute's pages on Statistics on the Web (mainly links to places with interesting data)
Andy Pryke's The Data Mine the first site on the web for data mining includes many web links ind bibliography
Data Mining Resources at National Center for Atmospheric Research
QOZI Statistics Resources portal
KDnuggets Data Mining & Knowledge Discovery news


coming (soon) ...

I've been planning for some time to make some online analysis tools, partly to support the large number of visitors to my statistics tutorial site, partly to support the HCI book site and AI book, and partly because it seems like a good idea.

Things that I expect to have here include:
data management (for small experiments)
online statistical analysis of data
online tests including significance levels
online questionnaire management
interesting data mining and AI algorithms

The difference between 'coming sometime' and 'coming soon' will be related to the level of interest you have. If you are interested in any of the above please tell me!


"the only statistics you can trust are those you falsified yourself"    Winston Churchill Alan Dix 26/4/2003