Re: Cause and effect

[Tuan V Nguyen <t.nguyen@garvan.unsw.edu.au>]

Hello VNSA folks,

	It is nice to see VNSA friends again. It is also quite 
pleasant to see the list being grown rapidly. 

	Re the above thread, can I ask Vu~ in which journal, 
issue number, pages, etc the above article was published? 

	I have not read this article, but it seems peculiar for 
a computer science expert who writes about the philosophical 
subject of "cause and effect". In fact, this is not a new 
topic; it has been a subject for discussion/argument among 
statisticians for almost 100 years! In the old days, they 
called this "causa aequat effectum". Many people believed in 
this principle so strongly that they were prepared to reject 
the Darwin theory of evolution. 

	I will consider this topic a little bit further when I 
have receoverd from my trip.


	Tuan V Nguyen




At 11:29 PM 13/03/97 -0600, you wrote:
>There's recently a very interesting article on the philosophical
>foundations of statistics that may be of interest to  statisticians, or
>economists or social scientists who extensively use statistical methods in
>their everyday professional life. The author is Professor Judea Pearl, one
>of the founding fathers of Bayesian network technology that has recently
>had revolutionary impacts on modern expert systems and, in general,
>artificial intelligence. Below is the abstract of the paper.
>
>Title: The New Challenge: From a Century of Statistics to an Age of
>Causation.
>Author: J. Pearl, Professor of Computer Science, UCLA.
>
>Abstract:
>
>	Some of the main users of statistical methods - economists, 
>	social scientists, and epidemiologists - are discovering that 
>	their fields rest not on statistical but on causal foundations. 
>	The blurring of these foundations over the years follows from  
>	the lack of mathematical notion capable of distinguishing 
>	causal from equational relationships. By providing formal 
>	and natural explications of such relations, graphical methods 
>	have the potential to revolutionize how statistics is used in 
>	knowledge-rich applications. Statisticians, in response, are 
>	beginning to realize that causality is not a metaphysical 
>	deadend but a meaningful concept with clear mathematical
>	underpinning. This paper survey these developements and 
>	outline future challenges. 
>
>
>For those who are interested, the article can be retrieved at
>
>	http://singapore.cs.ucla.edu/jp_home.html 
>
>Cheers,
>--  Vu~