On 1 Jun 2003 17:17:23 -0700, [EMAIL PROTECTED] (Serge) wrote: > Hello, > > I have to do a final project for my Statistics class. I chose to do a > project on the relationship between a car's weight and its 4 crash > test ratings (2 front for passenger and driver and 2 side for front > and rear). The ratings are 1 - 5 (the number of stars); the higher the > rating, the safer the car. I got all my data from crashtest.com. In > all, I got data for 187 cars - that is, the weight and the 4 ratings.
I see a note at crashtest.com, prominently on the first page of the site (using the address that someone else posted): "Keep in mind that crash test results shouldn't be compared among vehicles with large weight differences (more than 15%), so we have divided the vehicles into 5 distinct weight categories. " I would read that to be a STRONG indicator that you might need to read carefully about the standardization of various test results. Maybe you *can* compare everything if it *is* within one weight category, but I would want to know what sort of statement that "15%" is supposed to be. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
