Michael wrote...
"I find it very hard to believe that someone who lets say lived and died in the 
hills of Kentucky without leaving a local geographical area (with no phone or 
computer of course) would be 6 to 7 introductions away from a nomad who lived 
and died in the mountains of Afghanistan in a similar small geographic area."

Just for fun.... Man in Kentucky knows a guy (1) who's son (2) joined the army. 
The son was recently deployed to Afghanistan where he met a local man (3) who 
was assisting the US military there. The man in Afghanistan is the nephew of 
the nomad who is living in the mountains (4).

Now, the probability of this occurring is probably not that great, but it is 
not unreasonable either... especially when you consider that was only 4 steps 
and not the average 6.6. I can think of several other variations of the above 
that are all within 4-8 steps between the two. Just because the 2 individuals 
on either end of the chain are "remote and isolated" doesn't mean there aren't 
possible connections between them. (Admittedly it helped that you chose a 
country where the US military has been involved lately...) Also, the fact that 
the chain exists, does not say anything about the likelihood of the two people 
actually being introduced to each other, which in many cases is probably 
extremely rare and unlikely. It also depends on how we are going to actually 
define two people as knowing each other. Send an IM seems somewhat reasonable, 
but if I send an IM to a customer service representative at a web hosting 
company asking for support, does that mean that I actually "know" the person?

And as previously mentioned, it isn't saying that everyone is within 6 
connections because of the variability that likely exists.... Especially when 
you figure the connections between many people were likely 1 (ie they directly 
know each other) which could offset much more distant connections to average 
out at the 6.6 (I think that was the average). Knowing the variability (and 
skewness) of the distribution of connections would definitely be helpful in 
making sense of what it really means. I've deleted the original email at this 
point, but does anyone know what the range or standard deviation was for the 
number of connections? Also, does anyone know where this study itself (rather 
than a media report on it) has been published?

Back to grading papers...
-marc



========================================
G. Marc Turner, MEd, PhD
Senior Lecturer & Technology Coordinator
Department of Psychology
Texas State University-San Marcos
San Marcos, TX  78666
Phone: (512) 245-2526
E-mail: [EMAIL PROTECTED]<mailto:[EMAIL PROTECTED]>

---
To make changes to your subscription contact:

Bill Southerly ([EMAIL PROTECTED])

Reply via email to