WordNet

a quantity that is added or subtracted in order to increase the accuracy of a scientific measure (同)fudge factor
the act of offering an improvement to replace a mistake; setting right (同)rectification
a drop in stock market activity or stock prices following a period of increases; "market runups are invariably followed by a correction"
treatment of a specific defect; "the correction of his vision with eye glasses"
a rebuke for making a mistake (同)chastening, chastisement
something substituted for an error
the social control of offenders through a system of imprisonment and rehabilitation and probation and parole
the department of local government that is responsible for managing the treatment of convicted offenders; "for a career in corrections turn to the web site of the New Jersey Department of Corrections" (同)department of corrections

PrepTutorEJDIC

〈U〉『訂正』,修正,調整 / 〈C〉訂正箇所,訂正の書き入れ / 〈U〉(よくするための)処罰,叱責(しっせき)

Wikipedia preview

出典(authority):フリー百科事典『ウィキペディア（Wikipedia）』「2015/09/28 02:20:52」(JST)

wiki en

In statistics, the Bonferroni correction is a method used to counteract the problem of multiple comparisons. It is named after Italian mathematician Carlo Emilio Bonferroni for the use of Bonferroni inequalities,^[1] but modern usage is credited to Olive Jean Dunn, who first used it in a pair of articles written in 1959 and 1961.^[2]^[3]

Informal introduction

Statistical inference logic is based on rejecting the null hypotheses if the likelihood of the observed data under the null hypotheses is low. The problem of multiplicity arises from the fact that as we increase the number of hypotheses being tested, we also increase the likelihood of a rare event, and therefore, the likelihood of incorrectly rejecting a null hypothesis (i.e., make a Type I error).

The Bonferroni correction is based on the idea that if an experimenter is testing hypotheses, then one way of maintaining the familywise error rate (FWER) is to test each individual hypothesis at a statistical significance level of times what it would be if only one hypothesis were tested.

So, if the desired significance level for the whole family of tests should be (at most) , then the Bonferroni correction would test each individual hypothesis at a significance level of . For example, if a trial is testing eight hypotheses with a desired , then the Bonferroni correction would test each individual hypothesis at .

Statistically significant simply means that a given result is unlikely to have occurred by chance assuming the null hypothesis is actually correct (i.e., no difference among groups, no effect of treatment, no relation among variables).

Definition

^{[dubious – discuss]}

Let be a family of hypotheses and the corresponding p-values. Let be the (unknown) subset of the true null hypotheses, having members.

The familywise error rate is the probability of rejecting at least one of the members in ; that is, to make one or more type I error. The Bonferroni Correction states that choosing all will control the . The proof follows from Boole's inequality:

This result does not require that the tests be independent.

Modifications

Generalization

We have used the fact that , but the correction can be generalized and applied to any , as long as the weights are defined prior to the test.

Confidence intervals

Bonferroni correction can be used to adjust confidence intervals. If we are forming confidence intervals, and wish to have overall confidence level of , then adjusting each individual confidence interval to the level of will be the analog confidence interval correction.

Alternatives

There are other alternatives to control the familywise error rate. For example, the Holm–Bonferroni method and the Šidák correction are said to be uniformly more powerful test procedures than the Bonferroni correction.

Criticisms

The Bonferroni correction can be somewhat conservative if there are a large number of tests and/or the test statistics are positively correlated. The correction also comes at the cost of increasing the probability of producing false negatives, and consequently reducing statistical power.

Another criticism concerns the concept of a family of hypotheses. The statistical community has not reached a consensus on how to define such a family. As there is no standard definition, test results may change dramatically, only by modifying the way we consider the hypotheses families.

All of these criticisms, however, apply to adjustments for multiple comparisons in general, and are not specific to the Bonferroni correction.

References

^ Bonferroni, C. E., Teoria statistica delle classi e calcolo delle probabilità, Pubblicazioni del R Istituto Superiore di Scienze Economiche e Commerciali di Firenze 1936
^ Dunn, Olive Jean (1959). "Estimation of the Medians for Dependent Variables". Annals of Mathematical Statistics 30 (1): 192–197. JSTOR 2237135.
^ Dunn, Olive Jean (1961). "Multiple Comparisons Among Means" (PDF). Journal of the American Statistical Association 56 (293): 52–64. doi:10.1080/01621459.1961.10482090.

External links

School of Psychology, University of New England, New South Wales, Australia, 2000, http://www.une.edu.au/WebStat/unit_materials/c5_inferential_statistics/bonferroni.html
Weisstein, Eric W., "Bonferroni correction", MathWorld.
Bonferroni, Sidak online calculator
Explanation of p-value correction methods under the context of differential gene expression analysis

UpToDate Contents

全文を閲覧するには購読必要です。 To read the full text you will need to subscribe.

1. 浸透圧性脱髄症候群（ODS）および低ナトリウム血症の急速すぎる補正 osmotic demyelination syndrome ods and overly rapid correction of hyponatremia
2. 遺伝学およびゲノミクスのためのツール：遺伝子発現プロファイリング tools for genetics and genomics gene expression profiling
3. 遺伝関連研究：原理および応用 genetic association studies principles and applications
4. SPECT放射性核種心筋血流イメージングにおける減衰によるアーチファクト attenuation artifact in spect radionuclide myocardial perfusion imaging
5. 高ナトリウム血症の治療 treatment of hypernatremia

English Journal

Clinical validity of a DPYD-based pharmacogenetic test to predict severe toxicity to fluoropyrimidines.

Toffoli G1, Giodini L1, Buonadonna A2, Berretta M3, De Paoli A4, Scalone S2, Miolo G2, Mini E5, Nobili S6, Lonardi S7, Pella N8, Lo Re G9, Montico M1, Roncato R1, Dreussi E1, Gagno S1, Cecchin E1.
International journal of cancer. Journal international du cancer.Int J Cancer.2015 Dec 15;137(12):2971-80. doi: 10.1002/ijc.29654. Epub 2015 Jul 14.
Pre-therapeutic DPYD pharmacogenetic test to prevent fluoropyrimidines (FL)-related toxicities is not yet common practice in medical oncology. We aimed at investigating the clinical validity of DPYD genetic analysis in a large series of oncological patients. Six hundred three cancer patients, treate
PMID 26099996

STR-based genetic structure of the Berber population of Bejaia (Northern Algeria) and its relationships to various ethnic groups.

Amir N1, Sahnoune M2, Chikhi L3, Atmani D4.
Gene.Gene.2015 Dec 10;574(1):140-8. doi: 10.1016/j.gene.2015.08.002. Epub 2015 Aug 5.
Patterns of genetic variation in human populations have been described for decades. However, North Africa has received little attention and Algeria, in particular, is poorly studied, Here we genotyped a Berber-speaking population from Algeria using 15 short tandem repeat (STR) loci D8S1179, D21S11,
PMID 26253162

Effects of framework design and layering material on fracture strength of implant-supported zirconia-based molar crowns.

Kamio S1, Komine F1, Taguchi K1, Iwasaki T1, Blatz MB2, Matsumura H1.
Clinical oral implants research.Clin Oral Implants Res.2015 Dec;26(12):1407-13. doi: 10.1111/clr.12468. Epub 2014 Aug 12.
OBJECTIVES: To evaluate the effects of framework design and layering material on the fracture strength of implant-supported zirconia-based molar crowns.MATERIAL AND METHODS: Sixty-six titanium abutments (GingiHue Post) were tightened onto dental implants (Implant Lab Analog). These abutment-implant
PMID 25115334