Skip to content

stat question - not R question so ignore if not interested

4 messages · Richard M. Heiberger, Jonathan Baron, Bert Gunter +1 more

#
The missing piece is why there are two clusters.  There is
most likely a two-level factor distinguishing the groups
that was not included in the model.  It might not even have
been measured and now you need to find it.

Rich
#
A classic example used by my colleague Paul Rozin (when he
teaches Psych 1) is to compute the correlation between height
and number of shoes owned, in the class.  Shorter students own
more shoes.  But ...
On 12/05/06 16:34, Richard M. Heiberger wrote:

  
    
#
... But of course this is always the question underlying all empirical -- or
maybe even scientific -- analysis: is there some other perhaps more
fundamental variable out there that I'm missing that would explain what's
"really" going on?

I clearly remember George Box commenting on this in his Monday night beer
and statistics sessions: after you're done and perhaps have written up and
presented your (intricate!) analysis, you're always worried that someone
might come along and say, "Well, did you consider...?"

Cheers,
Bert 

Bert Gunter
Genentech Nonclinical Statistics
South San Francisco, CA 94404


-----Original Message-----
From: r-help-bounces at stat.math.ethz.ch
[mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Jonathan Baron
Sent: Tuesday, December 05, 2006 1:45 PM
To: Richard M. Heiberger
Cc: r-help at stat.math.ethz.ch; C. Park; Leeds,Mark (IED)
Subject: Re: [R] stat question - not R question so ignore if not interested

A classic example used by my colleague Paul Rozin (when he
teaches Psych 1) is to compute the correlation between height
and number of shoes owned, in the class.  Shorter students own
more shoes.  But ...
On 12/05/06 16:34, Richard M. Heiberger wrote: