Boole's inequality

(Redirected from Union bound)

In probability theory, Boole's inequality, also known as the union bound, says that for any finite or countable set of events, the probability that at least one of the events happens is no greater than the sum of the probabilities of the individual events. This inequality provides an upper bound on the probability of occurrence of at least one of a countable number of events in terms of the individual probabilities of the events. Boole's inequality is named for its discoverer, George Boole.[1]

Formally, for a countable set of events A1, A2, A3, ..., we have

In measure-theoretic terms, Boole's inequality follows from the fact that a measure (and certainly any probability measure) is σ-sub-additive.

Proof

edit

Proof using induction

edit

Boole's inequality may be proved for finite collections of   events using the method of induction.

For the   case, it follows that

 

For the case  , we have

 

Since   and because the union operation is associative, we have

 

Since

 

by the first axiom of probability, we have

 

and therefore

 

Proof without using induction

edit

For any events in  in our probability space we have

 

One of the axioms of a probability space is that if   are disjoint subsets of the probability space then

 

this is called countable additivity.

If we modify the sets  , so they become disjoint,

 

we can show that

 

by proving both directions of inclusion.

Suppose  . Then   for some minimum   such that  . Therefore  . So the first inclusion is true:  .

Next suppose that  . It follows that   for some  . And   so  , and we have the other inclusion:  .

By construction of each  ,  . For   it is the case that  

So, we can conclude that the desired inequality is true:

 

Bonferroni inequalities

edit

Boole's inequality may be generalized to find upper and lower bounds on the probability of finite unions of events.[2] These bounds are known as Bonferroni inequalities, after Carlo Emilio Bonferroni; see Bonferroni (1936).

Let

 

for all integers k in {1, ..., n}.

Then, when   is odd:

 

holds, and when   is even:

 

holds.

The equalities follow from the inclusion–exclusion principle, and Boole's inequality is the special case of  .

Proof for odd K

edit

Let  , where   for each  . These such   partition the sample space, and for each   and every  ,   is either contained in   or disjoint from it.

If  , then   contributes 0 to both sides of the inequality.

Otherwise, assume   is contained in exactly   of the  . Then   contributes exactly   to the right side of the inequality, while it contributes

 

to the left side of the inequality. However, by Pascal's rule, this is equal to

 

which telescopes to

 

Thus, the inequality holds for all events  , and so by summing over  , we obtain the desired inequality:

 

The proof for even   is nearly identical.[3]

Example

edit

Suppose that you are estimating 5 parameters based on a random sample, and you can control each parameter separately. If you want your estimations of all five parameters to be good with a chance 95%, what should you do to each parameter?

Tuning each parameter's chance to be good to within 95% is not enough because "all are good" is a subset of each event "Estimate i is good". We can use Boole's Inequality to solve this problem. By finding the complement of event "all five are good", we can change this question into another condition:

P( at least one estimation is bad) = 0.05 ≤ P( A1 is bad) + P( A2 is bad) + P( A3 is bad) + P( A4 is bad) + P( A5 is bad)

One way is to make each of them equal to 0.05/5 = 0.01, that is 1%. In other words, you have to guarantee each estimate good to 99%( for example, by constructing a 99% confidence interval) to make sure the total estimation to be good with a chance 95%. This is called the Bonferroni Method of simultaneous inference.

See also

edit

References

edit
  1. ^ Boole, George (1847). The Mathematical Analysis of Logic. Philosophical Library. ISBN 9780802201546.
  2. ^ Casella, George; Berger, Roger L. (2002). Statistical Inference. Duxbury. pp. 11–13. ISBN 0-534-24312-6.
  3. ^ Venkatesh, Santosh (2012). The Theory of Probability. Cambridge University Press. pp. 94–99, 113–115. ISBN 978-0-534-24312-8.
edit

This article incorporates material from Bonferroni inequalities on PlanetMath, which is licensed under the Creative Commons Attribution/Share-Alike License.