Editing Cosmic variance (section)

{{for|the weblog|Cosmic Variance (blog)}}
{{cosmology}}

The term '''''cosmic variance''''' is the [[Statistics|statistical]] [[uncertainty]] inherent in observations of the universe at extreme distances. It has three different but closely related meanings:
* It is sometimes used, incorrectly, to mean [[sample variance]] – the difference between different finite samples of the same parent population. Such differences follow a [[Poisson distribution]], and in this case the term [[sample variance]] should be used instead.
* It is sometimes used, mainly by cosmologists, to mean the uncertainty because we can only observe one realization of all the possible observable universes. For example, we can only observe one [[Cosmic Microwave Background]], so the measured positions of the peaks in the Cosmic Microwave Background spectrum, integrated over the visible sky,  are limited by the fact that only one  spectrum is observable from Earth. The observable universe viewed from another galaxy will have the peaks in slightly different places, while remaining consistent with the same physical laws, inflation, etc. This second meaning may be regarded as a special case of the third meaning.
* The most widespread use, to which the rest of this article refers, reflects the fact that measurements are affected by cosmic large-scale structure, so a measurement of any region of sky (viewed from Earth) may differ from a measurement of a different region of sky (also viewed from Earth) by an amount that may be much greater than the sample variance.

This most widespread use of the term is based on the idea that it is only possible to observe part of the universe at one particular time, so it is difficult to make statistical statements about [[physical cosmology|cosmology]] on the scale of the entire universe,<ref name="aspj">{{Cite journal | url=http://www.iop.org/EJ/article/1538-4357/600/2/L171/17416.html | author=Somerville | title=Cosmic Variance in the Great Observatories Origins Deep Survey | journal=The Astrophysical Journal Letters  | year=2004 | volume=600 | issue=2 | pages=L171–L174 | doi=10.1086/378628 | last2=Lee | first2=Kyoungsoo | last3=Ferguson | first3=Henry C. | last4=Gardner | first4=Jonathan P. | last5=Moustakas | first5=Leonidas A. | last6=Giavalisco | first6=Mauro|arxiv = astro-ph/0309071 |bibcode = 2004ApJ...600L.171S | citeseerx=10.1.1.255.7912 | s2cid=16650601 |display-authors=etal}}</ref><ref name="aas">{{Cite journal|url=http://www.aas.org/publications/baas/v37n4/aas207/1366.htm|bibcode=2005AAS...20717006K|title=Quantifying the Effects of Cosmic Variance Using the NOAO Deep-Wide Field Survey|journal=American Astronomical Society Meeting Abstracts|volume=207|pages=170.06|last1=Keremedjiev|first1=M. S.|last2=MacDonald|first2=E. C.|last3=Dey|first3=A.|last4=Jannuzi|first4=B. T.|year=2005|access-date=2007-09-18|archive-date=2008-01-02|archive-url=https://web.archive.org/web/20080102081508/http://www.aas.org/publications/baas/v37n4/aas207/1366.htm|url-status=dead}}</ref> as the number of observations ([[sample size]]) must be not too small.