Jump to content

Anscombe transform

From Wikipedia, the free encyclopedia
Standard deviation of the transformed Poisson random variable as a function of the mean m.

In statistics, the Anscombe transform, named after Francis Anscombe, is a variance-stabilizing transformation that transforms a random variable with a Poisson distribution into one with an approximately standard Gaussian distribution. The Anscombe transform is widely used in photon-limited imaging (astronomy, X-ray) where images naturally follow the Poisson law. The Anscombe transform is usually used to pre-process the data in order to make the standard deviation approximately constant. Then denoising algorithms designed for the framework of additive white Gaussian noise are used; the final estimate is then obtained by applying an inverse Anscombe transformation to the denoised data.

Anscombe transform animated. Here μ is the mean of the Anscombe-transformed Poisson distribution, normalized by subtracting by 2m+38−14m1/2, and σ is its standard deviation (estimated empirically). We notice that m3/2μ and m2(σ−1) remains roughly in the range of [0,10] over the period, giving empirical support for μ=O(m−3/2),σ=1+O(m−2)

Definition

[edit]

For the Poisson distribution the mean m and variance v are not independent: m=v. The Anscombe transform[1]

A:x↦2x+38

aims at transforming the data so that the variance is set approximately 1 for large enough mean; for mean zero, the variance is still zero.

It transforms Poissonian data x (with mean m) to approximately Gaussian data of mean 2m+38−14m1/2+O(1m3/2) and standard deviation 1+O(1m2). This approximation gets more accurate for larger m,[2] as can be also seen in the figure.

For a transformed variable of the form 2x+c, the expression for the variance has an additional term 38−cm; it is reduced to zero at c=38, which is exactly the reason why this value was picked.

Inversion

[edit]

When the Anscombe transform is used in denoising (i.e. when the goal is to obtain from x an estimate of m), its inverse transform is also needed in order to return the variance-stabilized and denoised data y to the original range. Applying the algebraic inverse

A−1:y↦(y2)2−38

usually introduces undesired bias to the estimate of the mean m, because the forward square-root transform is not linear. Sometimes using the asymptotically unbiased inverse[1]

y↦(y2)2−18

mitigates the issue of bias, but this is not the case in photon-limited imaging, for which the exact unbiased inverse given by the implicit mapping[3]

E⁡[2x+38∣m]=2∑x=0+∞(x+38⋅mxe−mx!)↦m

should be used. A closed-form approximation of this exact unbiased inverse is[4]

y↦14y2−18+1432y−1−118y−2+5832y−3.

Alternatives

[edit]

There are many other possible variance-stabilizing transformations for the Poisson distribution. Bar-Lev and Enis report[2] a family of such transformations which includes the Anscombe transform. Another member of the family is the Freeman-Tukey transformation[5]

A:x↦x+1+x.

A simplified transformation, obtained as the primitive of the reciprocal of the standard deviation of the data, is

A:x↦2x

which, while it is not quite so good at stabilizing the variance, has the advantage of being more easily understood. Indeed, from the delta method,

V[2x]≈(d(2m)dm)2V[x]=(1m)2m=1.

Generalization

[edit]

While the Anscombe transform is appropriate for pure Poisson data, in many applications the data presents also an additive Gaussian component. These cases are treated by a Generalized Anscombe transform[6] and its asymptotically unbiased or exact unbiased inverses.[7]

See also

[edit]

References

[edit]
  1. 1 2 Anscombe, F. J. (1948), "The transformation of Poisson, binomial and negative-binomial data", Biometrika, vol. 35, no. 3–4, [Oxford University Press, Biometrika Trust], pp. 246–254, doi:10.1093/biomet/35.3-4.246, JSTOR 2332343
  2. 1 2 Bar-Lev, S. K.; Enis, P. (1988), "On the classical choice of variance stabilizing transformations and an application for a Poisson variate", Biometrika, vol. 75, no. 4, pp. 803–804, doi:10.1093/biomet/75.4.803
  3. ↑ Mäkitalo, M.; Foi, A. (2011), "Optimal inversion of the Anscombe transformation in low-count Poisson image denoising", IEEE Transactions on Image Processing, vol. 20, no. 1, pp. 99–109, Bibcode:2011ITIP...20...99M, doi:10.1109/TIP.2010.2056693, PMID 20615809, S2CID 10229455
  4. ↑ Mäkitalo, M.; Foi, A. (2011), "A closed-form approximation of the exact unbiased inverse of the Anscombe variance-stabilizing transformation", IEEE Transactions on Image Processing, vol. 20, no. 9, pp. 2697–2698, Bibcode:2011ITIP...20.2697M, doi:10.1109/TIP.2011.2121085, PMID 21356615, S2CID 7937596
  5. ↑ Freeman, M. F.; Tukey, J. W. (1950), "Transformations related to the angular and the square root", The Annals of Mathematical Statistics, vol. 21, no. 4, pp. 607–611, doi:10.1214/aoms/1177729756, JSTOR 2236611
  6. ↑ Starck, J.L.; Murtagh, F.; Bijaoui, A. (1998). Image Processing and Data Analysis. Cambridge University Press. ISBN 978-0-521-59914-6.
  7. ↑ Mäkitalo, M.; Foi, A. (2013), "Optimal inversion of the generalized Anscombe transformation for Poisson-Gaussian noise", IEEE Transactions on Image Processing, vol. 22, no. 1, pp. 91–103, Bibcode:2013ITIP...22...91M, doi:10.1109/TIP.2012.2202675, PMID 22692910, S2CID 206724566

Further reading

[edit]