Statistics vs. Data Mining 2

[Clusty]

After reading the very interesant discussion about reporting and data mining on this forum (

http://www.tek-tips.com/viewthread.cfm?qid=441384&page=1),

I have found an interesting paper which is comparing (to a certain extent) statistics and data mining. The main question the author ask is whether data mining is statistics "déjà vu".

You can find the paper here:

http://www.tdan.com/print/5226

Sandro Saitta

http://www.dataminingblog.com

 

[Stella740pl]

Great article.
Thanks.

 

[Predictor]

Linked below is another paper on the subject of data mining versus statistics, "Data Mining and Statistics: What's the Connection?", by Friedman:

http://www-stat.stanford.edu/~jhf/ftp/dm-stat.pdf

-Will

 

[Clusty]

Hi,

Thanks for the link, the paper seems very interesting.



Sandro Saitta

http://www.dataminingblog.com

 

[johnherman]

I have always thought data mining and statistics were initimately connected, but I had taken 15 credits of stats in college, and was familiar with many of the techniques and their algorithms before "data mining" became a buzzword.

-------------------------
The trouble with doing something right the first time is that nobody appreciates how difficult it was - Steven Wright

 

[Clusty]

I understand your point of view. But at that time, the buzzword was maybe machine learning and not data mining. I personally see "data mining" and "statistics" as two different fields (although closely related). The way you approach the same problem is completely different from a statistic or from a data mining point of view.

Sandro Saitta

http://www.dataminingblog.com

http://www.website-ranking-search-engines.com