- to the world, and Dennis. On 13 Jan 2003 14:59:34 -0800, [EMAIL PROTECTED] (dennis roberts) wrote:
> At 04:07 PM 1/13/2003, Rich Ulrich wrote: > > >Exactly on this topic, I see a serious mis-statment in the document, > >under "Planning a study to yield a certain margin of error (M)". > > > >Where it says, > >"how large of a SAMPLE would I need, > >with 95% confidence, to produce an interval ...." - it ought to say, > >"... with 50% confidence, ..." > > > >since it is doing only the simplest extrapolation from the > >point-estimate of the SD the pilot study. That 95% was > >pulled out of thin air, or borrowed by accident (I guess) from > >the size of the CI. It is unaccounted for; it is a mistake. > >(But it is not surprising. This power stuff is tricky, and I think > > that I remember making that same mistake, back when I first > >started worrying about these, and before I found that "anchor.") > > are you saying that a 95% CI is a 50% CI? if so, explain > So, you *are* confusing the two assertions that you make, confusing likelihood of the outcome with the size of the CI. I tried to clarify how and why those differed. I Your statement should read, "How large of a SAMPLE would I need in order to have 50% assurance (power, confidence) that it will produce a 95% confidence interval of +/- .05 ... " I gave you the 100% assurance/ power version: variance is fixed (for example, polls). I explained why your result was 50%: point-estimate being replicated. I showed, by example, how you compute the actual power by using the chi squared distribution. Now I have explained what the problem is with your syntax, since you apparently fixed on (mis)reading your own, instead of reading what I contributed. You *made* a power statement. "... need, with 95% confidence" is distinct from " ... to produce a 95% confidence interval." That about covers it, except, if you have a textbook that sows so much confusion, I'm willing to write to the authors. But I suggest that you check exactly how they phrase whatever they say. [ ... ] -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
