Vickrey auction

2014-01-17T10:50:00Z

128.93.44.113: /* Self-revelation/incentive compatibility */

{{redirect|Bimodal|the musical concept|Bimodality}}

[[Image:Bimodal.png|thumb|'''Figure 1.''' A simple bimodal distribution, in this case a mixture of two [[normal distribution]]s with the same variance but different means. The figure shows the [[probability density function]] (p.d.f.), which is an average of the bell-shaped p.d.f.s of the two normal distributions.]]
[[Image:BimodalAnts.png|thumb|right|'''Figure 2.''' Histogram of body lengths of 300 weaver ant workers.<ref name="Weber1946">{{cite journal|author=Weber, NA|year=1946| title=Dimorphism in the African ''Oecophylla'' worker and an anomaly (Hym.: Formicidae)| journal=Annals of the Entomological Society of America| volume=39| pages=pp. 7–10| url=http://antbase.org/ants/publications/10434/10434.pdf|format=PDF}}</ref>]]
[[Image:Bimodal-bivariate-small.png|thumb|'''Figure 3.''' A bivariate, multimodal distribution.]]

In [[statistics]], a '''bimodal distribution''' is a [[continuous probability distribution]] with two different [[mode (statistics)|mode]]s. These appear as distinct peaks (local maxima) in the [[probability density function]], as shown in Figure 1.

More generally, a '''multimodal distribution''' is a continuous probability distribution with two or more modes, as illustrated in Figure 3.

==Terminology==

When the two modes are unequal the larger mode is known as the major mode and the other as the minor mode. The least frequent value between the modes is known as the [[antimode]]. The difference between the major and minor modes is known as the [[amplitude]]. In time series the major mode is called the [[acrophase]] and the antimode the [[batiphase]].

==Gatlung's classification==

Gatling introduced a classification system (AJUS) for distributions<ref name=Galtung1969>Galtung J (1969) Theory and methods of social research. Universitetsforlaget, Oslo ISBN 0043000177</ref>

*A: unimodal distribution - peak in the middle
*J: unimodal - peak at either end
*U: bimodal - peaks at both ends
*S: bimodal or multimodal - multiple peaks

This classification has since been modified slightly:

*J (modified) - peak on right
*L: unimodal - peak on left
*F: no peak (flat)

Under this classification bimodal distributions are classified as type S or U.

==Examples==

Bimodal distributions occur both in mathematics and in the natural sciences.

===Probability distributions===

Important bimodal distributions include the [[arcsine distribution]] and the [[beta distribution]]. Others include the [[U-quadratic distribution]].

The ratio of two normal distributions is also bimodally distributed. Let

: <math> R = \frac{ a + x }{ b + y } </math>

where ''a'' and ''b'' are constant and ''x'' and ''y'' are distributed as normal variables with a mean of 0 and a standard deviation of 1. ''R'' has a known density that can be expressed as a confluent [[hypergeometric function]].<ref name=Fieller1932>Fieller E (1932) The distribution of the index in a noraml bivariate population. Biometrika (24):428-440</ref>

The distribution of the [[Inverse distribution|reciprocal]] of a ''t'' distributed random variable is bimodal when the degrees of freedom are more than one. Similarly the reciprocal of a normally distributed variable is also bimodally distributed.

===Occurrences in nature===

Examples of variables with bimodal distributions include the time between eruptions of certain [[geyser]]s, the [[Galaxy color-magnitude diagram|color of galaxies]], the size of worker [[weaver ants]], the age of incidence of [[Hodgkin's lymphoma]], the speed of inactivation of the drug [[isoniazid]] in US adults, the absolute magnitude of [[nova]]e, and the [[Circadian rhythm|circadian activity patterns]] of those [[crepuscular]] animals that are active both in morning and evening twilight. In fishery science multimodal length distributions reflect the different year classes and can thus be used for age distribution- and growth estimates of the fish population<ref>[http://www.fao.org/docrep/W5449E/w5449e05.htm.|FAO: Introduction to tropical fish stock assessment]</ref> Sediments are usually distributed in a bimodal fashion.

==Origins==

{{main|Mixture distribution}}

===Mathematical===

A bimodal distribution most commonly arises as a mixture of two different [[unimodal]] distributions (i.e. distributions having only one mode). In other words, the bimodally distributed random variable X is defined as <math> Y </math> with probability <math> \alpha </math> or <math> Z </math> with probability <math> (1-\alpha), </math> where ''Y'' and ''Z'' are unimodal random variables and <math>0 < \alpha < 1</math> is a mixture coefficient.

Mixtures with two distinct components need not be bimodal and two component
mixtures of unimodal component densities can have more than two modes. There is no immediate connection between the number of components in a mixture and the number of modes of the resulting density.

===Biology===

In biology four factors are known to contribute to bimodal distributions of population sizes:

*the initial distribution of individual sizes

*the distribution of growth rates among the individuals

*the size and time dependence of the growth rate of each individual

* mortality rates that may affect each size class differently.

The bimodal distribution of sizes of [[weaver ant]] workers shown in Figure 2 arises due to existence of two distinct classes of workers, namely major workers and minor workers.<ref name="Weber1946"/> In this case, ''Y'' would be the size of a random major worker, ''Z'' the size of a random minor worker, and ''α'' the proportion of worker weaver ants that are major workers.

The [[distribution of fitness effects]] of mutations for both whole [[genome]]s<ref>{{cite journal|last=Sanjuán|first=R|title=Mutational fitness effects in RNA and single-stranded DNA viruses: common patterns revealed by site-directed mutagenesis studies.|journal=Philosophical transactions of the Royal Society of London. Series B, Biological sciences|date=2010 Jun 27|volume=365|issue=1548|pages=1975-82|pmid=20478892}}</ref><ref>{{cite journal|last=Eyre-Walker|first=A|coauthors=Keightley, PD|title=The distribution of fitness effects of new mutations.|journal=Nature reviews. Genetics|date=2007 Aug|volume=8|issue=8|pages=610-8|pmid=17637733}}</ref> and individual [[gene]]s<ref>{{cite journal|last=Hietpas|first=RT|coauthors=Jensen, JD; Bolon, DN|title=Experimental illumination of a fitness landscape.|journal=Proceedings of the National Academy of Sciences of the United States of America|date=2011 May 10|volume=108|issue=19|pages=7896-901|pmid=21464309}}</ref> is also frequently found to be bimodal with most [[mutations]] being either neutral or lethal with relatively few having intermediate effect.

==General properties==

A mixture of two unimodal distributions with differing means is not necessarily bimodal. The combined distribution of heights of men and women is sometimes used as an example of a bimodal distribution, but in fact the difference in mean heights of men and women is too small relative to their [[standard deviation]]s to produce bimodality.<ref name="Schilling2002">{{Cite journal|title=Is Human Height Bimodal?|first1=Mark F. |last1=Schilling |first2= Ann E.| last2=Watkins |first3=William |last3=Watkins| journal=[[The American Statistician]]| doi=10.1198/00031300265 |volume=56 |year=2002| pages=223–229 |issue=3}}</ref>

Bimodal distributions have the peculiar property that - unlike the unimodal distributions - the mean may be a more robust sample estimator than the median.<ref name=Mosteller1977>Mosteller F, Tukey JW (1977) Data analysis and regression: a second course in statistics. Reading, Mass, Addison-Wesley Pub Co</ref> This is clearly the case when the distribution is U shaped like the arcsine distribution. It may not be true when the distribution has one or more long tails.

===Moments of mixtures===

Let

: <math> f( x ) = p g_1( x ) + ( 1 - p ) g_2( x ) </math>

where ''g''i is a probability distribution and ''p'' is the mixing parameter.

The moments of ''f''(x) are<ref name=Kim2003>Kim T-H, White H (2003) [http://www.cirano.qc.ca/realisations/grandes_conferences/methodes_econometriques/white.pdf On more robust estimation of skewness and kurtosis: Simulation and application to the S & P 500 index]</ref>

: <math> \mu = p \mu_1 + ( 1 - p ) \mu_2 </math>

: <math> \nu_2 = p[ \sigma_1^2 + \delta_1^2 ] + ( 1 - p )[ \sigma_2^2 + \delta_2^2 ]</math>

: <math> \nu_3 = p [ S_1 \sigma_1^3 + 3 \delta_1 \sigma_1^2 + \delta_1^3 ] + ( 1 - p )[ S_2 \sigma_2^3 + 3 \delta_2 \sigma_2^2 + \delta_2^3 ] </math>

: <math> \nu_4 = p[ K_1 \sigma_1^4 + 4 S_1 \delta_1 \sigma_1^3 + 6 \delta_1^2 \sigma_1^2 + \delta_1^4 ] + ( 1 - p )[ K_2 \sigma_2^4 + 4 S_2 \delta_2 \sigma_2^3 + 6 \delta_2^2 \sigma_2^2 + \delta_2^4 ]</math>

where
: <math> \mu = \int{ x f( x ) dx }</math>

: <math> \delta_i = \mu_i - \mu </math>

: <math> \nu_r = \int{ ( x - \mu )^r f( x ) dx } </math>

and ''S''i and ''K''i are the skewness and kurtosis of the ''i''th distribution.

==Mixture of two normal distributions==

It is not uncommon to encounter situations where an investigator believes that the data comes from a mixture of two normal distributions. Because of this, this mixture has been studied in some detail.<ref name=Robertson1969>Robertson CA, Fryer JG (1969) Some descriptive properties of normal mixtures. Skandinavisk Aktuarietidskrift 69: 137–146</ref>

A mixture of two normal distributions has five parameters to estimate: the two means, the two variances and the mixing parameter. A mixture of two [[normal distribution]]s with equal [[standard deviation]]s is bimodal only if their means differ by at least twice the common standard deviation.<ref name="Schilling2002"/> Estimates of the parameters is simplified if the variances can be assumed to be equal (the [[homoscedastic]] case).

It is obvious that if the means of the two normal distributions are equal that the combined distribution is unimodal. Conditions for [[unimodality]] of the combined distribution were derived by Eisenberger.<ref name=Eisenberger1964>Eisenberger I (1964) Genesis of bimodal distributions. Technometrics 6 (4) 357-363</ref> Necessary and sufficient conditions for a mixture of normal distributions to be bimodal have been identified by Ray and Lindsay.<ref name=Ray2005>Ray S, Lindsay BG (2005) The topography of multivariate normal mixtures. Ann Stat 33 (5) 2042-2065</ref>

A mixture of two approximately equal mass normal distributions have a negative kurtosis since the two modes on either side of the center of mass effectively flatten out the distribution.

A mixture of two normal distributions with highly unequal mass have a positive kurtosis since the smaller distribution lengthens the tail of the more dominant normal distribution.

Mixtures of other distributions require additional parameters to be estimated.

===Mixture of two normal distributions with equal variances===

If the case of equal variance the mixture is unimodal if and only if<ref name=Holzmann2008>Holzmann H,Vollmer S (2008) A likelihood ratio test for bimodality in two-component mixtures – with application to regional income distribution in the EU. AStA 2(1)57-69</ref>

: <math> d \le 1 </math>

or

: <math> \left\vert \log( 1 - p ) - \log( p ) \right\vert \ge 2 \log( d - \sqrt{ d^2 - 1 } ) + 2d \sqrt{ d^2 - 1 } </math>

where ''p'' is the mixing parameter and ''d'' is

: <math> d = \frac{ \mu_1 - \mu_2 }{ 2 \sqrt{ \sigma_1 \sigma_2 } } </math>

where ''μ''1 and ''μ''2 are the means of the two normal distributions and ''σ''1 and ''σ''2 are their standard deviations.

==Summary statistics==

Bimodal distributions are a commonly used example of how summary statistics such as the [[mean]], [[median]], and [[standard deviation]] can be deceptive when used on an arbitrary distribution. For example, in the distribution in Figure 1, the mean and median would be about zero, even though zero is not a typical value. The standard deviation is also larger than deviation of each normal distribution.

Although several have been suggested, there is no presently generally agreed summary statistic (or set of statistics) to quantify the parameters of a general bimodal distribution. For a mixture of two normal distributions the mean and standard deviation along with the mixing parameter (a weighing system for the combination) are usually used - a total of five parameters.

===Ashman's D===

A statistic that may be useful is Ashman's D:<ref name=Ashman1994>Ashman KM, Bird CM, Zepf SE(1994) Astronomical J 108: 2348</ref>

: <math> D = 2^\frac{ 1 }{ 2 } \frac{ \left| \mu_1 - \mu_2 \right| }{ \sqrt{ ( \sigma_1^2 + \sigma_2^2 ) } } </math>

where ''μ''1, ''μ''2 are the means and ''σ''1 ''σ''2 are the standard deviations.

For a mixture of two normal distributions ''D'' > 2 is required for a clean separation of the distributions.

===Bimodality index===

The bimodality index assumes that the distribution is a sum of two normal distributions with equal variances but differing means.<ref name=Wang2009>Wang J, Wen S, Symmans WF, Pusztai L, Coombes KR (2009) The bimodality index: a criterion for discovering and ranking bimodal signatures from cancer gene expression profiling data. Cancer Inform 7:199-216</ref> It is defined as follow:

: <math> \delta = \frac{ | \mu_1 - \mu_2 |}{ \sigma } </math>

where ''μ''1, ''μ''2 are the means and ''σ'' is the common standard deviation.

: <math> BI = \delta \sqrt{ p( 1 - p ) } </math>

where ''p'' is the mixing parameter.

===Bimodal separation===

This index assumes that the distribution is a mixture of two normal distributions with means (''μ''1 and ''μ''2) and standard deviations (''σ''1 and ''σ''2):<ref name=Zhang2003>Zhang C, Mapes BE, Soden BJ (2003) Bimodality in tropical water vapour. Q J R. Meteorol Soc 129: 2847–2866 doi: 10.1256/qj.02.16</ref>

: <math> S = \frac{ \mu_1 - \mu_2 }{ 2( \sigma_1 +\sigma_2 ) } </math>

===Bimodality coefficient===

Sarle's bimodality coefficient ''b'' is<ref name=Ellision1987>Ellision AM (1987) Effect of seed dimorphism on the density-dependent dynamics of experimental populations of ''Atriplex triangularis'' (Chenopodiaceae). Am J Botany 74(8): 1280-1288</ref>

: <math> \beta = \frac{ \gamma^2 + 1 }{ \kappa } </math>

where ''γ'' is the [[skewness]] and ''κ'' is the [[kurtosis]]. The kurtosis is here defined to be the standardised fourth moment around the mean. The value of ''b'' lies between 0 and 1.<ref name=Pearson1916>Pearson K (1916) Mathematical contributions to the theory of evolution, XIX: Second supplement to a memoir on skew variation. Phil Trans Roy Soc London. Series A 216 (538–548): 429–457. Bibcode 1916RSPTA.216..429P. doi:10.1098/rsta.1916.0009. JSTOR 91092</ref> The logic behind this coefficient is that a bimodal distribution will have very low kurtosis, an asymmetric
character, or both - all of which increase this coefficient.

The formula for a finite sample is<ref name=SASInst2012>SAS Institute Inc. (2012). SAS/STAT 12.1 user’s guide. Cary, NC: Author.</ref>

: <math> b = \frac{ g^2 + 1 }{ k + \frac{ 3( n - 1 )^2 }{ ( n - 2 )( n - 3 ) } } </math>

where ''n'' is the number of items in the sample, ''g'' is the sample skewness and ''k'' is the sample excess kurtosis.

The value of ''b'' for the [[uniform distribution (continuous)|uniform distribution]] is 5/9. This is also its value for the [[exponential distribution]]. Values greater than 5/9 may indicate a bimodal or multimodal distribution. The maximum value (1.0) is reached only by a [[Bernoulli distribution]] with only two distinct values or the sum of two different [[Dirac delta function]]s.

The distribution of this statistic is unknown. It is related to a statistic proposed earlier by Pearson - the difference between the kurtosis and the square of the skewness (''vide infra'').

===Bimodality amplitude===

This is defined as<ref name=Zhang2003>Zhang C, Mapes BE, Soden BJ (2003) Bimodality in tropical water vapour. Q J R. Meteorol Soc 129: 2847–2866 doi: 10.1256/qj.02.16</ref>

: <math> A_B = \frac{A_1 - A_{ an } }{ A_1 } </math>

where ''A''1 is the amplitude of the smaller peak and ''A''an is the amplitude of the antinode.

''A''B is always < 1. Larger values indicate more distinct peaks.

===Bimodal ratio===

This is the ratio of the left and right peaks.<ref name=Zhang2003>Zhang C, Mapes BE, Soden BJ (2003) Bimodality in tropical water vapour. Q J R. Meteorol Soc 129: 2847–2866 doi: 10.1256/qj.02.16</ref> Mathematically

: <math> R = \frac{ A_r }{ A_l } </math>

where ''A''l and ''A''r are the amplitudes of the left and right peaks respectively.

===Bimodality parameter===

This parameter (''B'') is due to Wilcock.<ref name=Wilcock1993>Wilcock PR (1993) The critical shear stress of natural sediments. J Hydraul Engrg ASCE 119:491-505</ref>

: <math> B = \frac{ A_r }{ A_l } \sum P_i </math>

where ''A''l and ''A''r are the amplitudes of the left and right peaks respectively and ''P''i is the logarithm taken to the base 2 of the proportion of the distribution in the ith interval. The maximal value of ''B'' is 1.

==Statistical tests==

A number of tests are available to determine if a data set is distributed in a bimodal (or multimodal) fashion.

===Graphical methods===

In the study of sediments particle size is frequently bimodal. Empirically it has been found useful to plot the frequency against the log( size ) of the particles.<ref name=Folk1957>Folk RL, Ward WC (1957) Brazos River bar: a study in the significance of grain size parameters. J Sedim Petrol 27: 3–26</ref><ref name=Dyer1970>Dyer KR (1970) Grain-size parameters for sandy gravels. J Sedim Petrol 40 (2) 616-620</ref> This usually gives a clear separation of the particles into a bimodal distribution. In geological applications the [[logarithm]] is normally taken to the base 2. The log transformed values are referred to as phi (Φ) units. This system is known as the [[Grain size|Krumbein]] (or phi) scale.

An alternative method is to plot the log of the particle size against the cumulative frequency. This graph will usually consist two reasonably straight lines with a connecting line corresponding to the antimode.

;Statistics

Approximate values for several statistics can be derived from the graphic plots.<ref name=Folk1957>Folk RL, Ward WC (1957) Brazos River bar: a study in the significance of grain size parameters. J Sedim Petrol 27: 3–26</ref>

: <math>\mathit{Mean} = \frac{ \phi_{ 16 } + \phi_{ 50 } + \phi_{ 84 } }{ 3 }</math>

: <math>\mathit{StdDev} = \frac{ \phi_{ 84 } - \phi_{ 16 } }{ 4 } + \frac{ \phi_{ 95 } - \phi_{ 5 } }{ 6.6 } </math>

: <math>\mathit{Skew} = \frac{ \phi_{ 84 } + \phi_{ 16 } - 2 \phi_{ 50 } }{ 2 ( \phi_{ 84 } - \phi_{ 16 } ) } + \frac{ \phi_{ 95 } + \phi_{ 5 } - 2 \phi_{ 50 } }{ 2( \phi_{ 95 } - \phi_{ 5 } ) } </math>

: <math>\mathit{Kurt} = \frac{ \phi_{ 95 } - \phi_{ 5 } }{ 2.44 ( \phi_{ 75 } - \phi_{ 25 } ) }</math>

where ''Mean'' is the mean, ''StdDev'' is the standard deviation, ''Skew'' is the skewness, ''Kurt'' is the kurtosis and ''φ''x is the value of the variate ''φ'' at the ''x''th percentage of the distribution.

===Unimodal vs. bimodal distribution===

A necessary but not sufficient condition for a symmetrical distribution to be bimodal is that the [[kurtosis]] be less than three.<ref name=Gneddin2010>Gneddin OY(2010) Quantifying Bimodality.</ref><ref name=Muratov2010>Muratov AL, Gnedin OY (2010) Modeling the metallicity distribution of globular clusters. Ap J (submitted) arXiv:1002.1325</ref> Here the kurtosis is defined to be the standardised fourth moment around the mean. The reference given prefers to use the ''excess kurtosis'' - the kurtosis less 3.

Pearson in 1894 was the first to devise a procedure to test whether a distribution could be resolved into two normal distributions.<ref name=Pearson1894>Pearson K (1894) Contributions to the mathematical theory of evolution: On the dissection of asymmetrical frequency-curves. Phil Trans Roy Soc Series A, Part 1, 185: 71-90</ref> This method required the solution of a ninth order [[polynomial]]. In a subsequent paper Pearson reported that for any distribution skewness2 + 1 < kurtosis.<ref name=Pearson1916>Pearson K (1916) Mathematical contributions to the theory of evolution, XIX: Second supplement to a memoir on skew variation. Phil Trans Roy Soc London. Series A 216 (538–548): 429–457. Bibcode 1916RSPTA.216..429P. doi:10.1098/rsta.1916.0009. JSTOR 91092</ref> Later Pearson showed that<ref name=Pearson1929>Pearson K (1929) Editorial note. Biometrika 21: 370-375</ref>

: <math> b_2 - b_1 \ge 1 </math>

where ''b''2 is the kurtosis and ''b''1 is the square of the skewness. Equality holds only for the two point [[Bernoulli distribution]] or the sum of two different [[Dirac delta function]]s. These are the most extreme cases of bimodality possible. The kurtosis in both these cases is 1. Since they are both symmetrical their skewness is 0 and the difference is 1.

Baker proposed a transformation to convert a bimodal to a unimodal distribution.<ref name=Baker1930>Baker GA (1930) Transformations of bimodal distributions. Ann Math Stat 1 (4) 334-344</ref>

Several tests of unimodality versus bimodality have been proposed: Haldane suggested one based on second central differences.<ref name=Haldane1951>Haldane JBS (1951) Simple tests for bimodality and bitangentiality. Ann Eugenics 16 (1) 359–364 DOI: 10.1111/j.1469-1809.1951.tb02488.x</ref> Larkin later introduced a test based on the F test;<ref name=Larkin1979>Larkin RP (1979) An algorithm for assessing bimodality vs. unimodality in a univariate distribution. Behavior Research Methods 11 (4) 467-468 DOI: 10.3758/BF03205709</ref> Benett created one based on the G test.<ref name=Bennett1992>Bennett SC (1992) Sexual dimorphism of ''Pteranodon'' and other pterosaurs, with comments on cranial crests. J Vert Paleont 12 (4) 422-434</ref> Tokeshi has proposed fourth test.<ref name=Tokeshi1992>Tokeshi M (1992) Dynamics and distribution in animal communities; theory and analysis. Researches in Population Ecology 34:249–273</ref><ref name=Barreto2003>Barreto S, Borges PAV, Guo Q (2003) A typing error in Tokeshi’s test of bimodality. Global Ecology & Biogeography 12: 173–174</ref> A test based on a likelihood ratio has been proposed by Holzmann and Vollmer.<ref name=Holzmann2008>Holzmann H, Vollmer S (2008) A likelihood ratio test for bimodality in two-component mixtures – with application to regional income distribution in the EU. Advances in Statistical Analysis 92 (1) 57-69</ref>

===Antimode tests===

Statistical tests for the antimode are known.<ref name=Hartigan2000>Hartigan JA (2000) Testing for antimodes. Studies in Classification, Data Analysis, and Knowledge Organization 169-181</ref>

;Otsu's method

[[Otsu's method]] is commonly employed in computer graphics to determine the optimal separation between two distributions.

===General tests===

To test if a distribution is other than unimodal, several additional tests have been devised: the [[bandwidth test (multimodal)|bandwidth test]],<ref name=Silverman1981>Silverman BW (1981) Using kernel density estimates to investigate multimodality. J Roy Statist Soc Ser B 43:97-99</ref> the [[dip test]],<ref name=Hartigan1985>Hartigan JA, Hartigan PM (1985) The dip test of unimodality. Ann Statist 13 (1) 70-84</ref> the [[excess mass test]],<ref name=Mueller1991>Mueller DW, Sawitzki G (1991) Excess mass estimates and tests for multimodality. JASA 86, 738 -746</ref> the [[MAP test]],<ref name=Rozál1994>Rozál GPM Hartigan JA (1994) The MAP test for multimodality. J Classification 11 (1) 5-36 DOI: 10.1007/BF01201021</ref> the [[mode existence test]],<ref name=Minnotte1997>Minnotte MC (1997) Nonparametric testing of the existence of modes. Ann Statist 25 (4) 1646-1660</ref> the [[runt test]],<ref name=Hartigan1992>Hartigan JA, Mohanty S (1992) The RUNT test for multimodality. J Classifcation 9: 63-70</ref><ref name=Andrushkiw2008>Andrushkiw RI, Klyushin DD, Petunin YI (2008) Theory Stoch Processes 14 (1) 1-6</ref> the [[span test]],<ref name=Hartigan1988>Hartigan JA (1988) The span test of multimodality</ref> and the [[saddle test]].

The dip test is available for use in R.[http://cran.r-project.org/web/packages/diptest/index.html] The values for the dip statistic values range between 0 to 1. Values less than 0.05 indicating significant bimodality and values greater than 0.05 but less than 0.10 suggesting bimodality with marginal significance.

===Silverman's test===

Silverman introduced a bootstrap method for the number of modes.<ref name=Silverman1981>Silverman BW (1981) Using kernel density estimates to investigate multimodality. J Roy Stat Soc Ser B 43: 97–99</ref> The test uses a fixed bandwidth which reduces the power of the test and its interpretability. Under smoothed densities may have an excessive number of modes whose count during bootstrapping is unstable.

===Special cases===

Additional tests are available for a number of special cases

;Mixture of two normal distributions

A study of a mixture density of two normal distributions data found that separation into the two normal distributions was difficult unless the means were separated by 4-6 standard deviations.<ref name=Jackson1898>Jackson PR, Tucker GT, Woods HF (1989) Testing for bimodality in frequency distributions of data suggesting polymorphisms of drug metabolism--hypothesis testing. Br J Clin Pharmacol 28(6) 655–662</ref>

In [[astronomy]] the Kernel Mean Matching algorithm is used to decide if a data set belongs to a single normal distribution or to a mixture of two normal distributions.

;Beta-normal distribution

This distribution is bimodal for certain values of is parameters. A test for these values has been described.<ref>http://www.amstat.org/sections/srms/Proceedings/y2002/Files/JSM2002-000150.pdf</ref>

==Parameter estimation and fitting curves==

Assuming that the distribution is known to be bimodal or has been shown to be bimodal by one or more of the tests above, it is frequently desirable to fit a curve to the data. This may be difficult.

Bayesian methods may be useful in difficult cases.

===Software===

;Two normal distributions

A package for [[R]] is available for testing for bimodality.[http://www.uni-marburg.de/fb12/stoch/research/rpackage/manualbimodlilitytest.pdf] This package assumes that the data are distributed as a sum of two normal distributions. If this assumption is not correct the results may not be reliable. It also includes functions for fitting a sum of two normal distributions to the data.

Assuming that the distribution is a mixture of two normal distributions then the expectation-maximization algorithm may be used to determine the parameters. Several programmes are available for this including Cluster.<ref>https://engineering.purdue.edu/~bouman/software/cluster/</ref>

;Other distributions

The mixtools package also available for R can test for and estimate the parameters of a number of different distributions.<ref>http://cran.r-project.org/web/packages/mixtools/index.html</ref>

Another package for a mixture of two right tailed gamma distributions is available.<ref>http://cran.r-project.org/web/packages/discrimARTs/discrimARTs.pdf</ref>

Several other packages for R are available to fit mixture models: these include flexmix,<ref>http://cran.r-project.org/web/packages/flexmix/index.html</ref> mcclust,<ref>http://cran.r-project.org/web/packages/mclust/index.html</ref> mixdist<ref>http://cran.r-project.org/web/packages/mixdist/index.html</ref>

The programme SWRC ﬁt can fit a number of bimodal distributions.[http://www.hydrol-earth-syst-sci-discuss.net/4/407/2007/hessd-4-407-2007-print.pdf]

The statistical programme SAS can also fit a variety of mixed distributions with the command PROCFREQ.

==See also==
* [[Overdispersion]]

==References==
{{reflist|2}}

{{ProbDistributions}}

{{DEFAULTSORT:Bimodal Distribution}}
[[Category:Probability distributions]]
[[Category:Continuous distributions]]

formulasearchengine - User contributions [en]

Vickrey auction