The application of random coincidence graphs for testing the homogeneity of data
Choose points \(x_1, \dots, x_n\) independently and uniformly from the unit interval \(I\). The random interval graph \({\mathcal I} {\mathcal G}_{n,d}\) has vertices \(1,\dots,n\) and, for \(i\neq j\), edges \(\{i,j\}\) whenever \(| x_i-x_j |\leq d\). In this survey paper, the authors give exact results for the distribution of the degree of a vertex; the number of isolated vertices; and the number of components in \({\mathcal I}{\mathcal G}_{n,d}\). Consequently, for certain \(d=d (n)\), the distribution of the degree of a vertex; and the number of components of order \(k\) \((\geq 1)\) in \({\mathcal I}{\mathcal G}_{n,d}\) tend to a Poisson distribution with appropriate parameter as \(n\to\infty\). Generally, choose vectors \(\vec x_1,\dots,\vec x_n\) independently and uniformly from \(I^q\). The random coincidence graph \({\mathcal C}{\mathcal G}_{q,n,d}\) has vertices \(1,\dots,n\) and, for \(i\neq j\), edges \(\{i,j\}\) whenever \(\|\vec x_i-\vec x_j\|\leq d\) \((\| \cdot \|\) is the uniform norm). An exact result is given for the distribution of the degree of a vertex in \({\mathcal C}{\mathcal G}_{q,n,d}\). Again, for certain \(d=d(n)\), the distribution of the number of edges in \({\mathcal C}{\mathcal G}_{q,n,d}\) tends to a Poisson distribution with appropriate parameter as \(n\to \infty\). A discussion of the appropriateness of using random coincidence graphs when testing cluster structure in data sets is given. For the entire collection see [Zbl 0889.00025].
- Testing multivariate uniformity based on random geometric graphs
- Random association of symmetric arrays
- scientific article; zbMATH DE number 17201 (Why is no real title available?)
- scientific article; zbMATH DE number 1222136 (Why is no real title available?)
- scientific article; zbMATH DE number 912690 (Why is no real title available?)
- Distance-based parametric bootstrap tests for clustering of species ranges
This page was built for publication: The application of random coincidence graphs for testing the homogeneity of data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4217766)
