On Thu, 27 Nov 2008 22:05:02 -0500, Christopher D. Green wrote: >[snip] > There is no significance test I know of > associated with odds ratios (but apparently there isn't one associated > with Cox either).
I don't have the time right now to get involved in this thread but I did want to address the comment Chris made above. Of course there are significance tests and confidence itntervalas for odds ratios, logistic regression would be pointless if this weren't so. For more info on how to calculate the statistical significance of a single odds ratio (null hypothesis is that the odds ratio = 1.00 or there is no relationship) see the following on books.google.com: http://books.google.com/books?id=bmwhcJqq01cC&pg=PA542&dq=%22significance+test%22+%22odds+ratio%22&lr=&num=100#PPA542,M1 or http://tinyurl.com/5zx4dv -Mike Palij New York University [EMAIL PROTECTED] --- To make changes to your subscription contact: Bill Southerly ([EMAIL PROTECTED])
