In statistics, the use of Bayes factors is a Bayesian alternative to classical hypothesis testing.^{[1]}^{[2]} Bayesian model comparison is a method of model selection based on Bayes factors.
Contents

Definition 1

Interpretation 2

Example 3

See also 4

Notes 5

References 6

External links 7
Definition
The posterior probability Pr(MD) of a model M given data D is given by Bayes' theorem:

\Pr(MD) = \frac{\Pr(DM)\Pr(M)}{\Pr(D)}.
The key datadependent term Pr(DM) is a likelihood, and represents the probability that some data are produced under the assumption of this model, M; evaluating it correctly is the key to Bayesian model comparison.
Given a model selection problem in which we have to choose between two models, on the basis of observed data D, the plausibility of the two different models M_{1} and M_{2}, parametrised by model parameter vectors \theta_1 and \theta_2 is assessed by the Bayes factor K given by

K = \frac{\Pr(DM_1)}{\Pr(DM_2)} = \frac{\int \Pr(\theta_1M_1)\Pr(D\theta_1,M_1)\,d\theta_1} {\int \Pr(\theta_2M_2)\Pr(D\theta_2,M_2)\,d\theta_2} .
If instead of the Bayes factor integral, the likelihood corresponding to the maximum likelihood estimate of the parameter for each model is used, then the test becomes a classical likelihoodratio test. Unlike a likelihoodratio test, this Bayesian model comparison does not depend on any single set of parameters, as it integrates over all parameters in each model (with respect to the respective priors). However, an advantage of the use of Bayes factors is that it automatically, and quite naturally, includes a penalty for including too much model structure.^{[3]} It thus guards against overfitting. For models where an explicit version of the likelihood is not available or too costly to evaluate numerically, approximate Bayesian computation can be used for model selection in a Bayesian framework,^{[4]} with the caveat that approximateBayesian estimates of Bayes factors are often biased.^{[5]}
Other approaches are:
Interpretation
A value of K > 1 means that M_{1} is more strongly supported by the data under consideration than M_{2}. Note that classical hypothesis testing gives one hypothesis (or model) preferred status (the 'null hypothesis'), and only considers evidence against it. Harold Jeffreys gave a scale for interpretation of K:^{[6]}

K

dHart

bits

Strength of evidence

< 10^{0}

< 0


negative (supports M_{2})

10^{0} to 10^{1/2}

0 to 5

0 to 1.6

barely worth mentioning

10^{1/2} to 10^{1}

5 to 10

1.6 to 3.3

substantial

10^{1} to 10^{3/2}

10 to 15

3.3 to 5.0

strong

10^{3/2} to 10^{2}

15 to 20

5.0 to 6.6

very strong

> 10^{2}

> 20

> 6.6

decisive

The second column gives the corresponding weights of evidence in decihartleys (also known as decibans); bits are added in the third column for clarity. According to I. J. Good a change in a weight of evidence of 1 deciban or 1/3 of a bit (i.e. a change in an odds ratio from evens to about 5:4) is about as finely as humans can reasonably perceive their degree of belief in a hypothesis in everyday use.^{[7]}
An alternative table, widely cited, is provided by Kass and Raftery (1995):^{[3]}

2 ln K

K

Strength of evidence

0 to 2

1 to 3

not worth more than a bare mention

2 to 6

3 to 20

positive

6 to 10

20 to 150

strong

>10

>150

very strong

The use of Bayes factors or classical hypothesis testing takes place in the context of inference rather than decisionmaking under uncertainty. That is, we merely wish to find out which hypothesis is true, rather than actually making a decision on the basis of this information. Frequentist statistics draws a strong distinction between these two because classical hypothesis tests are not coherent in the Bayesian sense. Bayesian procedures, including Bayes factors, are coherent, so there is no need to draw such a distinction. Inference is then simply regarded as a special case of decisionmaking under uncertainty in which the resulting action is to report a value. For decisionmaking, Bayesian statisticians might use a Bayes factor combined with a prior distribution and a loss function associated with making the wrong choice. In an inference context the loss function would take the form of a scoring rule. Use of a logarithmic score function for example, leads to the expected utility taking the form of the Kullback–Leibler divergence.
Example
Suppose we have a random variable that produces either a success or a failure. We want to compare a model M_{1} where the probability of success is q = ½, and another model M_{2} where q is unknown and we take a prior distribution for q that is uniform on [0,1]. We take a sample of 200, and find 115 successes and 85 failures. The likelihood can be calculated according to the binomial distribution:

.
Thus we have

P(X=115 \mid M_1)={200 \choose 115}\left({1 \over 2}\right)^{200}=0.005956...,\,
but

P(X=115 \mid M_2)=\int_{0}^1{200 \choose 115}q^{115}(1q)^{85}dq = {1 \over 201} = 0.004975....
The ratio is then 1.197..., which is "barely worth mentioning" even if it points very slightly towards M_{1}.
This is not the same as a classical likelihoodratio test, which would have found the maximum likelihood estimate for q, namely ^{115}⁄_{200} = 0.575, whence \textstyle P(X=115 \mid M_2) = = 0.056991 (rather than averaging over all possible q). That gives a likelihood ratio of 0.1045, and so pointing towards M_{2}.
The modern method of relative likelihood takes into account the number of free parameters in the models, unlike the classical likelihood ratio. The relative likelihood method could be applied as follows. Model M_{1} has 0 parameters, and so its AIC value is 2·0 − 2·ln(0.005956) = 10.2467. Model M_{2} has 1 parameter, and so its AIC value is 2·1 − 2·ln(0.056991) = 7.7297. Hence M_{1} is about exp((7.7297 − 10.2467)/2) = 0.284 times as probable as M_{2} to minimize the information loss. Thus M_{2} is slightly preferred, but M_{1} cannot be excluded.
A frequentist hypothesis test of M_{1} (here considered as a null hypothesis) would have produced a very different result. Such a test says that M_{1} should be rejected at the 5% significance level, since the probability of getting 115 or more successes from a sample of 200 if q = ½ is 0.0200, and as a twotailed test of getting a figure as extreme as or more extreme than 115 is 0.0400. Note that 115 is more than two standard deviations away from 100.
M_{2} is a more complex model than M_{1} because it has a free parameter which allows it to model the data more closely. The ability of Bayes factors to take this into account is a reason why Bayesian inference has been put forward as a theoretical justification for and generalisation of Occam's razor, reducing Type I errors.^{[8]}
See also

Statistical ratios
Notes

^ Goodman S (1999). "Toward evidencebased medical statistics. 1: The P value fallacy" (PDF). Ann Intern Med 130 (12): 995–1004.

^ Goodman S (1999). "Toward evidencebased medical statistics. 2: The Bayes factor" (PDF). Ann Intern Med 130 (12): 1005–13.

^ ^{a} ^{b} Robert E. Kass and Adrian E. Raftery (1995). "Bayes Factors" (PDF). Journal of the American Statistical Association 90 (430): 791.

^ Toni, T.; Stumpf, M.P.H. (2009). "Simulationbased model selection for dynamical systems in systems and population biology" (PDF). Bioinformatics 26 (1): 104–10.

^ Robert, C.P., J. Cornuet, J. Marin and N.S. Pillai (2011). "Lack of confidence in approximate Bayesian computation model choice". Proceedings of the National Academy of Sciences 108 (37): 15112–15117.

^ H. Jeffreys (1961). The Theory of Probability (3 ed.). Oxford. p. 432

^

^ Sharpening Ockham's Razor On a Bayesian Strop
References

Bernardo, J.; Smith, A. F. M. (1994). Bayesian Theory. John Wiley.

Denison, D. G. T.; Holmes, C. C.; Mallick, B. K.; Smith, A. F. M. (2002). Bayesian Methods for Nonlinear Classification and Regression. John Wiley.

Duda, Richard O.; Hart, Peter E.; Stork, David G. (2000). "Section 9.6.5". Pattern classification (2nd ed.). Wiley. pp. 487–489.

Gelman, A.; Carlin, J.; Stern, H.; Rubin, D. (1995). Bayesian Data Analysis. London:

Jaynes, E. T. (1994), Probability Theory: the logic of science, chapter 24.

Lee, P. M. (2012). Bayesian Statistics: an introduction. Wiley.

Winkler, Robert (2003). Introduction to Bayesian Inference and Decision (2nd ed.). Probabilistic.
External links

BayesFactor —an R package for computing Bayes factors in common research designs

Bayes Factor Calculators —webbased version of much of the BayesFactor package
This article was sourced from Creative Commons AttributionShareAlike License; additional terms may apply. World Heritage Encyclopedia content is assembled from numerous content providers, Open Access Publishing, and in compliance with The Fair Access to Science and Technology Research Act (FASTR), Wikimedia Foundation, Inc., Public Library of Science, The Encyclopedia of Life, Open Book Publishers (OBP), PubMed, U.S. National Library of Medicine, National Center for Biotechnology Information, U.S. National Library of Medicine, National Institutes of Health (NIH), U.S. Department of Health & Human Services, and USA.gov, which sources content from all federal, state, local, tribal, and territorial government publication portals (.gov, .mil, .edu). Funding for USA.gov and content contributors is made possible from the U.S. Congress, EGovernment Act of 2002.
Crowd sourced content that is contributed to World Heritage Encyclopedia is peer reviewed and edited by our editorial staff to ensure quality scholarly research articles.
By using this site, you agree to the Terms of Use and Privacy Policy. World Heritage Encyclopedia™ is a registered trademark of the World Public Library Association, a nonprofit organization.