Null model: Difference between revisions

Revision as of 14:44, 16 November 2012

Latest revision as of 05:49, 12 April 2025

(39 intermediate revisions by 23 users not shown)

Line 1:

{{for|use in statistical testing|Statistical model}}

{{dead end|date=November 2012}}

{{for|use in ecology|Theoretical ecology}}

{{one source |date=April 2024}}

In mathematics, for example in the study of statistical properties of [[Graph (discrete mathematics)|graphs]], a '''null model''' is a type of random object that matches one specific object in some of its features, or more generally satisfies a collection of constraints, but which is otherwise taken to be an unbiasedly random structure. The null model is used as a term of comparison, to verify whether the object in question displays some non-trivial features (properties that wouldn't be expected on the basis of chance alone or as a consequence of the constraints), such as [[community structure]] in graphs. An appropriate null model behaves in accordance with a reasonable [[null hypothesis]] for the behavior of the system under investigation.

TheOne '''null model''' canof be a graph which matches the originalutility in some of its structural features, but which is otherwise a random graph. The null model is used as a term of comparison, to verify whether the graph at study displaysof community[[complex structure or not. The most popular null modelnetworks]] is that proposed by [[Mark Newman|Newman]] and [[Michelle Girvan|Girvan]], and consisitsconsisting of a randomized version of thean original graph <math>G</math>, whereproduced through edges arebeing rewired at random, under the constraint that the expected degree of each vertex matches the degree of the vertex in the original graph.<ref>{{cite journal|last=M.E.J|first=Newman|coauthors author-link=Mark Newman |author2=M.Girvan |author2-link= Michelle Girvan |title=Finding and evaluating community structure in networks|journal=Phys. Rev. E|year=2004|volume=69|issue=2|doi=10.1103/physreve.69.026113 |arxiv=cond-mat/0308217|bibcode=2004PhRvE..69b6113N|pmid=14995526|page=026113}}</ref>

The null model is the basic concept behind the definition of [[Modularity (networks)|modularity]], a function which evaluates the goodness of partitions of a graph into clusters. In particular, given a graph <math>G</math> and a specific community partition <math>\sigma:V(G)\rightarrow \{1,...,b\}</math> (an assignment of a community-index <math>\sigma(v)</math> (here taken as an integer from <math>1</math> to <math>b</math>) to each vertex <math>v\in V(G)</math> in the graph), the modularity measures the difference between the number of links from/to each pair of communities, from that expected in a graph that is completely random in all respects other than the set of degrees of each of the vertices (the [[degree sequence]]). In other words, the modularity contrasts the exhibited community structure in <math>G</math> with that of a null model, which in this case is the [[configuration model]] (the maximally random graph subject to a constraint on the degree of each vertex).

The null model is the basic concept behind the definition of modularity, a function which evaluates the goodness of partitions of a graph into clusters.

==ReferencesSee also==

* [[Null hypothesis]]

==References==

<references />

{{DEFAULTSORT:Null Model}}

{{stub}}

[[Category:Graph theory]]

[[Category:Statistical methods]]

{{graph-stub}}