Without context this is a shot in the dark, but my guess is this is referring to something like a logistic regression where the odds ratio (exponential of the coefficient) refers to the change in odds for the outcome for a 1 unit change in x. Now often a 1 unit change in x is very meaningful, but other times it is not that meaningful, e.g. if x is measuring the size of diamonds in carats and the data does not span an entire carat, or x is measured in days and our x variable spans years. In these cases it can make more sense to talk about the change in the odds relative to a different step size than just a 1 unit change in x, a reasonable thing to use is the change in odds for a one standard deviation change in x (much smaller than 1 for the diamonds, much larger for the days), this may be the odds ratio per standard deviation that you mention.
On Tue, Jun 11, 2013 at 7:38 PM, vinhnguyen04x <imvi...@yahoo.com.vn> wrote: > Hi all > > i have a question: > > why and when do we use odds ratio per standard deviation instead of odds > ratio? > > > > -- > View this message in context: > http://r.789695.n4.nabble.com/odds-ratio-per-standard-deviation-tp4669315.html > Sent from the R help mailing list archive at Nabble.com. > > ______________________________________________ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > -- Gregory (Greg) L. Snow Ph.D. 538...@gmail.com [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.