--- In [email protected], anonymousff <[EMAIL PROTECTED]> wrote:
> --- In [email protected], "authfriend" <[EMAIL PROTECTED]> 
> wrote:
> > --- In [email protected], anonymousff <[EMAIL PROTECTED]> 
> > wrote:
> > > --- In [email protected], "authfriend" <[EMAIL PROTECTED]> 
> > > > But that's exactly what this myth does: it provides
> > > > a basis for quantification.  From it we can construct
> > > > testable hypotheses, e.g., people who live in homes
> > > > with south-facing entrances will die at younger ages
> > > > than those in homes with entrances facing in other
> > > > directions.
> > > 
> > > Yes but...
> > > 
> > > You can do research that shows a correlation between factors, 
> and 
> > even 
> > > gives an indication of which factors may be causal. This is 
> > important 
> > > preliminary research. But, when faced with overwhelming 
> opposition 
> > to 
> > > your ideas due to their not fitting with mainstream paradigms, 
> you 
> > > need to follow up this research with studies that demonstrate 
> the 
> > > actual causal mechanisms for the results being observed.
> > 
> > I'm not sure you can actually *demonstrate* causal
> > mechanisms.  Rather, you make causal *assumptions*
> > to a greater or lesser confidence level, no?
> 
> ***
> Yeh, sure. To be technically correct. But this doesn't change the 
> nature of the research. One kind of research finds correlations, 
> without looking at what may cause the correlations. Another kind of 
> research focuses more directly on the processes involved.

On another front, I have been looking at the correlation / causation
question. At times I do a lot of multi-variate regression work where
say, 10 independent variables clearly "explain" most of the variations
in the dependent variable. This can lull one into believing that this
demonstrates causality. As a proof it does not, though it may still be
a causal relationship and the relationships can be mapped out using
influence diagrams.

Some interesting links on loosely and formally proving causality are
below:

http://b-course.hiit.fi/naive_cause.html

The scientific research community has adopted rigorous methods to
eliminate the need for subjective judgments about many things, but
when it comes to testing whether X causes Y, they revert to intuition
and hand-waving. This book makes a strong argument that we shouldn't
accept that. It demonstrates that it is possible to turn intuitions
about causation into hypotheses that are unambiguous and testable. 
http://www.psych.uni-goettingen.de/abt/1/waldmann/cog_sci00.pdf

http://www.amazon.com/exec/obidos/tg/detail/-/0521773628/102-3865279-2055340?v=glance

online version of the above:

http://bayes.cs.ucla.edu/BOOK-2K/book-toc.html




------------------------ Yahoo! Groups Sponsor --------------------~--> 
Get fast access to your favorite Yahoo! Groups. Make Yahoo! your home page
http://us.click.yahoo.com/dpRU5A/wUILAA/yQLSAA/JjtolB/TM
--------------------------------------------------------------------~-> 

To subscribe, send a message to:
[EMAIL PROTECTED]

Or go to: 
http://groups.yahoo.com/group/FairfieldLife/
and click 'Join This Group!' 
Yahoo! Groups Links

<*> To visit your group on the web, go to:
    http://groups.yahoo.com/group/FairfieldLife/

<*> To unsubscribe from this group, send an email to:
    [EMAIL PROTECTED]

<*> Your use of Yahoo! Groups is subject to:
    http://docs.yahoo.com/info/terms/
 



Reply via email to