At 08:39 AM 11/18/2002, User968758 wrote:
THIS IS what you see, too often, in discussions of CIs ... and, it is understandable since, it is simple to say this"So if you take a good random sample and compute a 95% confidence interval, there is a 95% chance that the true population parameter is within the computed interval."
but, if we modify this (which is a bit more cumbersome) to say:
the p value for producing a CI in a similar way ... for having produced an interval that does contain mu ... is .95 ...
or
put all possible 95% CIs in a big hat ... reach in at random and pull out one ... the p value for pulling out one that contains the parameter is ... .95
however, when all is said and done ... the fact remains that, while the probability is NOT .95 for THAT specific interval YOU get (it's 1 or 0) ... odds are darn good that it does contain the parameter ...
Absolutely not true. . . ================================================================= 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/ . =================================================================
