(redirected from posterior odds)
Also found in: Dictionary, Thesaurus, Legal.


The ratio of probability of occurrence to nonoccurrence of an event.
[pl. of odd, fr. M.E. odde, fr. O.Norse oddi, odd number]


In statistics, the probability that an event may appear or occur. This probability is estimated from known rates of occurrence of the event in a specific setting, e.g., from the known number of patients with a particular disease on a particular island. In practice most patients do not live on islands, and many have diseases whose presentation varies from the norm. The use of odds in health care always implies some degree of probability rather than of proof.


a method of expressing probability, e.g. at odds of 3 to 2 this can be converted to conventional terminology by using each number as the numerator and the sum of them as the denominator, i.e. 3/5, 2/5 or 60% or 40% or 0.6, 0.4. The odds are quoted as for or against. So that at odds of 3 to 2 the chances for an event happening are 3/5. The odds against it happening are 2/5.

posterior odds
probability determined after consideration of the results of a study.
odds ratio
the ratio, used particularly in case-control studies, estimates the chances of a particular event occurring in one population in relation to its rate of occurrence in another population.

Patient discussion about odds

Q. I have weak pelvic muscles.. Ive not had any children or anything like that. And im only 20. Isnt it abit odd It dont help one little bit when you have bladder problems(and struggle to control the flow)

A. Thank you for the answer Lucy, however i forgot to mention i have actually been doing P

More discussions about odds
References in periodicals archive ?
Theorem 2: The posterior odds ratio, denoted by [[beta].
Theorem 3: The posterior odds ratio, denoted by [[beta].
We estimated and tested that model against the conventional Neokeynesian model with inflation indexation using Bayesian analysis and showed that the posterior odds supports the lack of credibility model.
05 level rather than just above), and the posterior odds favor the model that excludes the Green Book forecasts, this time by about 10 to 1, which is approaching the decisive range.
This prior is in conjugate form, so that, combined with the likelihood, it can be integrated analytically to provide posterior odds on models.
Bayes' Theorem posits that the posterior odds of the proposition equal the prior odds times the likelihood ratio.
Thus, all other things being equal, the posterior odds will be higher: (a) the higher the prior odds; (b) the higher the probability that the evidence would arise given the troth of the proposition; and (c) the lower the probability that the evidence would arise given that the proposition is false.
All other things being equal, the lower the prior odds favoring the proposition that Matcher is the source, the lower the posterior odds -- the odds assessed with the DNA evidence taken into account -- in favor of the proposition; recall that, according to Bayes's Theorem, the posterior odds of a proposition equal the prior odds of the proposition times the likelihood ratio.
The prior odds of guilt are many times greater in the typical confirmation case than in the typical trawl case; if the likelihood ratio of the DNA evidence is approximately the same in the two cases, then the posterior odds -- assessed after all the evidence is in -- will also be much greater in the confirmation case than in the trawl case.
Sims (2003) criticized the use of posterior odds between DSGE models and VARs with diffuse prior because they do not provide a realistic characterization of model uncertainty.
The posterior odds that X shot Y will therefore be 4 to 1.
While Bayesian posterior odds favor the 'full-information' version of the model, the fall of inflation and interest rates in the disinflation episode in the early 1980's is better captured by the delayed response of the 'learning' specification.

Full browser ?