Hi, Actually, the reason for the test is to determine which is the better segment to target. A colleague of mine contended that with a mailing of 25000 and a response rate of approximately 0.5%, one can expect about 125 responses which is not sufficient to determine how the test fared against the control.
Any thoughts? Thanks. Brad "Arthur J. Kendall" <[EMAIL PROTECTED]> wrote in message news:<[EMAIL PROTECTED]>... > Knowing only what is in your post, that you want to compare the 6 > groups, I would say that you want equal sample sizes. If your dv is > response rate, you are probably ok. However, you should use poisson > estimates in comparing the rates. For other dv's you need to argue > strongly that nonresponse is not related to what answer would be given > if you could know the "true" answer. > > Hope this helps. > > Art > [EMAIL PROTECTED] > Social Research Consultants > University Park, MD USA > > > Brad Branford wrote: > > >Hi, > > > >I'm in the Direct Mail business. Given an expected response rate of > >0.50% how do you think the mail quantity (150,000) should be split > >among 6 groups (5 test and 1 control) ? > > > >Thanks in advance. > > > >Brad > > > > . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
