Bayes' theorem

From Wikipedia, the free encyclopedia

Jump to: navigation, search

This article is about the theorem. For its application in legal evidence diagnostics and Ediscovery, see Bayesian theory in E-discovery. For its application in marketing, see Bayesian
theory in marketing. For other uses, see Bayes theorem (disambiguation).

The simple statement of Bayes' theorem

Bayesian statistics

Theory
Bayesian probability
Probability interpretations

Bayes' theorem
Bayes' rule Bayes factor
Bayesian inference
Bayesian network

Prior Posterior Likelihood

Conjugate prior
Posterior predictive
Hyperparameter Hyperprior

Principle of indifference
Principle of maximum entropy

Empirical Bayes method

Cromwell's rule
Bernsteinvon Mises theorem
Bayesian information criterion
Credible interval
Maximum a posteriori estimation
Techniques
Bayesian linear regression
Bayesian estimator
Approximate Bayesian computation
Uses
Bayesian spam filtering
Binary classification
Naive Bayes classifier

In probability theory and statistics, Bayes' theorem (alternatively Bayes' law or Bayes' rule) is
a theorem with two distinct interpretations. In the Bayesian interpretation, it expresses how a
subjective degree of belief should rationally change to account for evidence. In the frequentist
interpretation, it relates inverse representations of the probabilities concerning two events. In the
Bayesian interpretation, Bayes' theorem is fundamental to Bayesian statistics, and has
applications in fields including science, engineering, economics (particularly microeconomics),
game theory, medicine and law. The application of Bayes' theorem to update beliefs is called
Bayesian inference.
Bayes' theorem is named for Thomas Bayes (/bez/; 17011761), who first suggested using the
theorem to update beliefs. His work was significantly edited and updated by Richard Price before
it was posthumously read at the Royal Society. The ideas gained limited exposure until they were
independently rediscovered and further developed by Laplace, who first published the modern
formulation in his 1812 Thorie analytique des probabilits. Until the second half of the 20th
century, the Bayesian interpretation was largely rejected by the mathematics community as
unscientific[citation needed]. However, it is now widely accepted. This may have been due to the

development of computing, which enabled the successful application of Bayesianism to many

complex problems.[1]

Contents
[hide]

1 Introductory example

2 Statement and interpretation

o 2.1 Bayesian interpretation
o 2.2 Frequentist interpretation

3 Forms
o 3.1 For events

3.1.1 Simple form

3.1.2 Extended form

3.1.3 Three or more events

o 3.2 For random variables

3.2.1 Simple form

3.2.2 Extended form

o 3.3 Bayes' rule

4 Derivation
o 4.1 For general events
o 4.2 For random variables

5 Examples
o 5.1 Frequentist example

o 5.2 Drug testing

6 History

7 Notes
o 7.1 Further reading

8 External links

[edit] Introductory example

Suppose someone told you they had a nice conversation with someone on the train. Not knowing
anything else about this conversation, the probability that they were speaking to a woman is
50%. Now suppose they also told you that this person had long hair. It is now more likely that
they were speaking to a woman, since most long-haired people are women. Bayes' theorem can
be used to calculate the probability that the person is a woman.
To see how this is done, let
represent the event that the conversation was held with a woman, and
denote the event that the conversation was held with a long-haired person.
It can be assumed that women constitute half the population for this example. So, not knowing
anything else, the probability that
occurs is
.
Suppose it is also known that 75% of women have long hair, which we denote as

(read: the probability of event

given event

is 0.75).

Likewise, suppose it is known that 30% of men have long hair, or

,
where
is the complementary event of
, i.e., the event that the conversation was held with a
man (assuming that every human is either a man or a woman).

Our goal is to calculate the probability that the conversation was held with a woman, given the
fact that the person had long hair, or, in our notation,
theorem, we have:

. Using the formula for Bayes'

where we have used the law of total probability. The numeric answer can be obtained by
substituting the above values into this formula. This yields
,
i.e., the probability that the conversation was held with a woman, given that the person had long
hair, is about 71%.

[edit] Statement and interpretation

Mathematically, Bayes' theorem gives the relationship between the probabilities of
and

, and the conditional probabilities of

given

and

given

and

,
and

. In its most common form, it is:

The meaning of this statement depends on the interpretation of probability ascribed to the terms:

[edit] Bayesian interpretation

Main article: Bayesian probability
In the Bayesian (or epistemological) interpretation, probability measures a degree of belief.
Bayes' theorem then links the degree of belief in a proposition before and after accounting for
evidence. For example, suppose somebody proposes that a biased coin is twice as likely to land
heads than tails. Degree of belief in this might initially be 50%. The coin is then flipped a
number of times to collect evidence. Belief may rise to 70% if the evidence supports the
proposition.
For proposition

and evidence

, the prior, is the initial degree of belief in

, the posterior, is the degree of belief having accounted for

represents the support

provides for

For more on the application of Bayes' theorem under the Bayesian interpretation of probability,
see Bayesian inference.

[edit] Frequentist interpretation

Illustration of frequentist interpretation with tree diagrams. Bayes' theorem connects conditional
probabilities to their inverses.
In the frequentist interpretation, probability measures a proportion of outcomes. Bayes' theorem
under this interpretation is most easily visualized using tree diagrams, as shown to the right. The
two diagrams partition the same population in different ways. The upper diagram partitions the
population into two groups, with and without property , and then partitions each group into
two further groups, with and without property . The lower diagram proceeds in reverse, first
partitioning according to and then according to . (For example, might be having a risk
factor for a medical condition, and might be having the condition.)
If we pick every member of a population with property

, and ask "what proportion of these

have property ?", this gives the probability

. Conversely, if we pick every member of
the same population with property and ask "what proportion of these have property ?" this
gives the probability
.
is the overall proportion with , and
the overall
proportion with . Bayes' theorem links these probabilities, which are in general different.

[edit] Forms
[edit] For events
[edit] Simple form
For events

and

, provided that

In a Bayesian inference step, the probability of evidence is constant for all models
posterior may then be expressed as proportional to the numerator:

. The

[edit] Extended form

Often, for some partition

of the event space, the event space is given or conceptualized in

terms of
probability:

. It is then useful to eliminate

and

using the law of total

In the special case of a binary partition,

[edit] Three or more events

Extensions to Bayes' theorem may be found for three or more events. For example, for three
events, two possible tree diagrams branch in the order BCA and ABC. By repeatedly applying
the definition of conditional probability:

As previously, the law of total probability may be used to substitute for unknown marginal
probabilities.

[edit] For random variables

Diagram illustrating the meaning of Bayes' theorem as applied to an event space generated by
continuous random variables and . Note that there exists an instance of Bayes' theorem for
each point in the domain. In practise, these instances might be parametrised by writing the
specified probability densities as a function of and .
Consider a sample space generated by two random variables and . In principle, Bayes'
theorem applies to the events
and
. However, terms become 0
at points where either variable has finite probability density. To remain useful, Bayes' theorem
may be formulated in terms of the relevant densities (see Derivation).
[edit] Simple form
If

is continuous and

If

is discrete and

If both

and

is discrete,

is continuous,

are continuous,

[edit] Extended form

Diagram illustrating how an event space generated by continuous random variables X and Y is
often conceptualized.
A continuous event space is often conceptualized in terms of the numerator terms. It is then
useful to eliminate the denominator using the law of total probability. For
an integral:

, this becomes

[edit] Bayes' rule

Main article: Bayes' rule
Under the Bayesian interpretation of probability, Bayes' rule may be thought of as Bayes'
theorem in odds form.

where

.
So the rule says that the posterior odds are the prior odds times the Bayes factor.

[edit] Derivation
[edit] For general events
Bayes' theorem may be derived from the definition of conditional probability:

[edit] For random variables

For two continuous random variables and
from the definition of conditional density:

, Bayes' theorem may be analogously derived

[edit] Examples
[edit] Frequentist example

Tree diagram illustrating frequentist example. R, C, P and P bar are the events representing rare,
common, pattern and no pattern. Percentages in parentheses are calculated. Note that three
independent values are given, so it is possible to calculate the inverse tree (see figure above).
An entomologist spots what might be a rare subspecies of beetle, due to the pattern on its back.
In the rare subspecies, 98% have the pattern. In the common subspecies, 5% have the pattern.
The rare subspecies accounts for only 0.1% of the population. How likely is the beetle to be rare?
From the extended form of Bayes' theorem,

[edit] Drug testing

Tree diagram illustrating drug testing example. U, U bar, "+" and "" are the events representing
user, non-user, positive result and negative result. Percentages in parentheses are calculated.
Suppose a drug test is 99% sensitive and 99% specific. That is, the test will produce 99% true
positive results for drug users and 99% true negative results for non-drug users. Suppose that
0.5% of people are users of the drug. If a randomly selected individual tests positive, what is the
probability he or she is a user?

Despite the apparent accuracy of the test, if an individual tests positive, it is more likely that they
do not use the drug than that they do.
This surprising result arises because the number of non-users is very large compared to the
number of users, such that the number of false positives (0.995%) outweighs the number of true
positives (0.495%). To use concrete numbers, if 1000 individuals are tested, there are expected to
be 995 non-users and 5 users. From the 995 non-users,
false positives are
expected. From the 5 users,
true positives are expected. Out of 15 positive
results, only 5, about 33%, are genuine.

[edit] History
Bayes' theorem was named after the Reverend Thomas Bayes (170261), who studied how to
compute a distribution for the probability parameter of a binomial distribution (in modern
terminology). His friend Richard Price edited and presented this work in 1763, after Bayes'
death, as An Essay towards solving a Problem in the Doctrine of Chances.[2] The French
mathematician Pierre-Simon Laplace reproduced and extended Bayes' results in 1774, apparently
quite unaware of Bayes' work.[3] Stephen Stigler suggested in 1983 that Bayes' theorem was
discovered by Nicholas Saunderson some time before Bayes[4]. However, this interpretation has
been disputed.[5]
Stephen Fienberg describes the evolution from "inverse probability" at the time of Bayes and
Laplace, a term still used by Harold Jeffreys (1939), to "Bayesian" in the 1950s.[6] Ironically,
Ronald A. Fisher introduced the "Bayesian" label in a derogatory sense[citation needed].

[edit] Notes
1.

^ McGrayne, Sharon Bertsch. (2011). The Theory That Would Not Die: How Bayes' Rule
Cracked The Enigma Code, Hunted Down Russian Submarines, & Emerged Triumphant from
Two Centuries of Controversy. New Haven: Yale University Press. 13-ISBN 9780300169690/10ISBN 0300169698; OCLC 670481486 The Theory That Would Not Die, p. 10. at Google Books

2.

^ Bayes, Thomas, and Price, Richard (1763). "An Essay towards solving a Problem in the
Doctrine of Chance. By the late Rev. Mr. Bayes, communicated by Mr. Price, in a letter to John
Canton, M. A. and F. R. S.". Philosophical Transactions of the Royal Society of London 53 (0):
370418. doi:10.1098/rstl.1763.0053. http://www.stat.ucla.edu/history/essay.pdf.

3.

^ Daston, Lorraine (1988). Classical Probability in the Enlightenment. Princeton Univ

Press. p. 268. ISBN 0-691-08497-1.

4.

^ Stigler, Stephen M. (1983), "Who Discovered Bayes' Theorem?" The American

Statistician 37(4):290296.

5.

^ Edwards, A. W. F. (1986), "Is the Reference in Hartley (1749) to Bayesian Inference?",

The American Statistician 40(2):109110

6.

^ Fienberg, Stephen E. (2006).When Did Bayesian Inference Become Bayesian?.

[edit] Further reading

Pierre-Simon Laplace. (1774/1986), "Memoir on the Probability of the Causes of

Events", Statistical Science 1(3):364378.

Stephen M. Stigler (1986), "Laplace's 1774 Memoir on Inverse Probability", Statistical

Science 1(3):359363.

Bayes rule: A Tutorial Introduction by JV Stone.

[edit] External links

Earliest Known Uses of Some of the Words of Mathematics (B). Contains origins of
"Bayesian", "Bayes' Theorem", "Bayes Estimate/Risk/Solution", "Empirical Bayes", and
"Bayes Factor".

Bayesian Statistics summary from Scholarpedia.

Weisstein, Eric W., "Bayes' Theorem" from MathWorld.

Bayes' theorem at PlanetMath

A tutorial on probability and Bayes theorem devised for Oxford University psychology
students

A graphical explanation of the Bayes theorem.

Retrieved from "http://en.wikipedia.org/w/index.php?title=Bayes

%27_theorem&oldid=511657135"
View page ratings

Rate this page

What's this?
Trustworthy

Objective

Complete

Well-written

I am highly knowledgeable about this topic (optional)

Submit ratings
Saved successfully
Your ratings have not been submitted yet
Categories:

Bayesian statistics

Probability theorems

Statistical theorems

Hidden categories:

All articles with unsourced statements

Articles with unsourced statements from February 2012

Articles with unsourced statements from March 2010