anogva: ANOGVA Analysis Of Graph Variability In statGraph: Statistical Methods for Graphs

Description

'anogva' statistically tests whether two or more sets of graphs are generated by the same random graph model. It is a generalization of the 'graph.test' function.

Usage

 `1` ```anogva(graphs, labels, numBoot = 1000, bandwidth = "Silverman") ```

Arguments

 `graphs` a list of adjacency matrices. For unweighted graphs, each matrix contains only 0s and 1s. For weighted graphs, each matrix may contain nonnegative real values that correspond to the weights of the edges. `labels` an array of integers indicating the labels of each graph. `numBoot` integer indicating the number of bootstrap resamplings. `bandwidth` string indicating which criterion will be used to choose the bandwidth for the spectral density estimation. The available criteria are "Silverman" (default) and "Sturges".

Value

A list containing:

 `statistic` the statistic of the test. `p.value` the p-value of the test.

References

Fujita, A., Vidal, M. C. and Takahashi, D. Y. (2017) A Statistical Method to Distinguish Functional Brain Networks. _Front. Neurosci._, *11*, 66. doi:10.3389/fnins.2017.00066.

Takahashi, D. Y., Sato, J. R., Ferreira, C. E. and Fujita A. (2012) Discriminating Different Classes of Biological Networks by Analyzing the Graph Spectra Distribution. _PLoS ONE_, *7*, e49949. doi:10.1371/journal.pone.0049949.

Silverman, B. W. (1986) _Density Estimation_. London: Chapman and Hall.

Sturges, H. A. The Choice of a Class Interval. _J. Am. Statist. Assoc._, *21*, 65-66.

Examples

 ``` 1 2 3 4 5 6 7 8 9 10 11 12 13 14``` ```require(igraph) g1 <- g2 <- g3 <- list() for (i in 1:20) { G1 <- erdos.renyi.game(50, 0.50) g1[[i]] <- get.adjacency(G1) G2 <- erdos.renyi.game(50, 0.50) g2[[i]] <- get.adjacency(G2) G3 <- erdos.renyi.game(50, 0.52) g3[[i]] <- get.adjacency(G3) } g <- c(g1, g2, g3) label <- c(rep(1,20),rep(2,20),rep(3,20)) result <- anogva(g, label, numBoot=50) result ```

statGraph documentation built on May 29, 2017, 9:08 a.m.