Has it become acceptable in teaching to just fit a curve to data points
and not report a correlation coefficient to indicate how well the curve
fits? American Biology Teacher author Stanley Rice seems to think so and
justifies his position because "most classes taught by readers of this
journal would not be prepared for these analyses." ABT 66: 475.
A correlation coefficient seems like a simple enough concept even for
students with little knowledge of statitics. Why bother to fit a curve
to the data if there is no indication of how well it fits?
David R. Hershey
_______________________________________________
Join Excite! - http://www.excite.com
The most personalized portal on the Web!
---
