At 08:10 PM 11/17/2002, Elliot Cramer wrote:
this is precisely why we don't adopt things like 38% CIs ... or 49% CIs ... we would like the odds to be in our favorI treat it as a bet where on repeated samples I bet that mu is in the region. I win 95% of the time
another way to illustrate the above is to, when your CI is calculated ... draw out a long number line ... which would contain all the theoretically possible values of the variable of interest ... section off the segment that the CI occupies ... and THEN offer the bet ...
you say ... i bet (whatever) mu is in this segment ... and as long as you have more than one bet ... you are bound to come out ahead (of course, the problem is trying to find a naiive person to take your bets!)
. . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
_________________________________________________________ dennis roberts, educational psychology, penn state university 208 cedar, AC 8148632401, mailto:[EMAIL PROTECTED] http://roberts.ed.psu.edu/users/droberts/drober~1.htm
. . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
