At 04:45 PM 9/17/02 -0500, Simon, Steve, PhD wrote:

>The interpretation here makes little sense to me. A car's mileage cannot 
>cause its Weight or Displacement.


gee ... according to what i have heard ... it all depends on how you define 
"cause"
(but, i agree with you)


>A good regression model for this data would use Weight and Drv.Rat as 
>independent variables. This model accounts for 89% of the variation in 
>MPG. I don't see how Corresponding Regressions can either replicate these 
>findings or develop any new insights into this data set.
>
>It could be that this data set is unusual.

what? this is a perfectly legitimate data set ... if the model can't handle 
it ... let's don't blame the data

.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to