A ratio of events to non-events; a measure of relative effect of an intervention that allows comparison between an intervention group and a control group.
The numerator is the intervention group; the denominator is the control group.
If the odds ratio, or OR, is > 1 the control is better than the intervention.
If the OR is < 1 the intervention is better than the control.
For example: a researcher is comparing mortality when using a statin vs. placebo. There are 10 in the statin group and 10 controls.
The odds for mortality for the statin group is 0.4 (4 of the 10 died, 4/10).
The odds for mortality for the placebo group is 0.8 (8 of the 10 died, 8/10).
The odds ratio would equal 0.5 (0.4/0.8), meaning that the odds of death when using the statin are 50% less than placebo.