Linda Palmer posted this URL, about the difference between relative risk and
odds ratio.  I found it lacked a clear explanation of exactly how RR and OR
are calculated using a four-celled grid, but parts of the discussion were
still edifying.  I'm including it again here.

http://www.childrens-mercy.org/stats/journal/oddsratio.asp

This article confirms what I thought, that odds ratios must be inverted if
you want to look at the odds the other way round.
If you know the odds ratio for two things, and you want people to compare
them in the opposite roles, you invert the odds ratio.  You don't subtract.
Thus, if breastfed babies get an illness half as often as formula fed
babies, you can say that the formula fed babies get the illness twice as
often as the breastfed babies.  The ratio one to two, inverted, is two to
one.  I am writing this in text because the characters I need to set up the
equation are the ones that typically get garbled on Lactnet.

Susan mentioned subtracting, but I still can't figure out what I would
subtract from what.

Rachel Myr
Kristiansand, Norway

             ***********************************************

Archives: http://community.lsoft.com/archives/LACTNET.html
Mail all commands to [log in to unmask]
To temporarily stop your subscription: set lactnet nomail
To start it again: set lactnet mail (or [log in to unmask])
To unsubscribe: unsubscribe lactnet or ([log in to unmask])
To reach list owners: [log in to unmask]