Talk:Landau distribution

This article is rated Start-class on Wikipedia's content assessment scale. It is of interest to the following WikiProjects:

Statistics Low‑importance This article is within the scope of WikiProject Statistics, a collaborative effort to improve the coverage of statistics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.StatisticsWikipedia:WikiProject StatisticsTemplate:WikiProject StatisticsStatistics articles Low This article has been rated as Low-importance on the importance scale.

It should be noted that the Landau distribution has no free parameters! Thus, the curve in the figure is wrong. There is no Landau distribution with a most probable value of 2 and a ${\displaystyle \sigma }$ of 1. Actually the most probable value is (ROOT TMath::Landau()) around 0.222.
Just by scaling and shifting one can introduce artificially a most probable value and a width

${\displaystyle x\rightarrow {\frac {x-MPV}{\sigma }}-0.222}$

Deserves its own page too, and link back and forth.82.171.225.84 (talk) 21:09, 16 August 2011 (UTC)[reply]

Could someone who knows add a section on why this is the distribution of particles' energy loss travelling through a thin medium?

Is there a mistake in the approximation given? (which is used for the figure).

${\displaystyle p(x)={\frac {1}{\sqrt {2\pi }}}\exp \left\{-{\frac {1}{2}}(x+e^{-x})\right\}.}$

This has a peak at x=-0.001 p=0.242. Whereas the integral (evaluated with scipy)

${\displaystyle p(x)={\frac {1}{\pi }}\int _{0}^{\infty }\!e^{-t\log t-xt}\sin(\pi t)\,dt.}$

give a peak at x=-0.223, p=0.181 which agrees with GSL:

#!/usr/bin/env python
import numpy
from matplotlib import pyplot
import pygsl.rng
x = numpy.linspace(-4, 10, 1000)
pyplot.plot(x, pygsl.rng.landau_pdf(x))
pyplot.show()

195.194.110.142 (talk) 14:15, 13 January 2015 (UTC)[reply]

When I plotted the second approximation vs GSL, it appears to look only vaguely like the Landau distribution and has the wrong tail behaviour. The tail isn't even a power law, so it can't be correct just by inspection. Skewray (talk) 17:49, 29 July 2023 (UTC)[reply]

The figure should show the parameter values used.

--Scharleb (talk) 19:05, 9 December 2021 (UTC)[reply]

This appears to have been fixed, although the approximation figure may have other issues. Skewray (talk) 19:26, 29 July 2023 (UTC)[reply]

The properties section is unnecessary. All those properties follow from the Landau distributions being stable. Skewray (talk) 19:25, 29 July 2023 (UTC)[reply]

I have to set μ = π/2 log (π/2) in order to get the Landau distribution to match the parametrization given for stable distributions in the stable distributions article. Does this article use a different stable distribution parametrization? There are at least ten in use... Skewray (talk) 15:50, 4 October 2023 (UTC)[reply]