If you want to approach this using hypothesis testing, what is the null hypothesis? No shift in preference? No systematic shift in preference? (Given the strong initial preference, I'm not sure what a "non-systematic shift" would look like.)
The best statistical technique might be "point and grunt." Michael T. Scoles, Ph.D. Interim Chair, Dept. Psychology & Counseling University of Central Arkansas Conway, AR 72035 --- You are currently subscribed to tips as: archive@jab.org To unsubscribe send a blank email to [EMAIL PROTECTED]