>"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." > >Absolutely not true.
>Care to explain? Suppose, for the sake of argument, that your computed 95% CI for mu is (3.1, 7.6). You want to say P(3.1<mu<7.6)=.95 ??? There's no random variable involved here, at least in the usual frequentist setup. Again, the "confidence" is associated with the process used to produce the interval, not with the particular interval you end up with. . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
