# graph.acf: Auto Correlation Function Estimation for Graphs In statGraph: Statistical Methods for Graphs

## Description

The function 'graph.acf' computes estimates of the autocorrelation function for graphs.

## Usage

 `1` ```graph.acf(x, plot = TRUE) ```

## Arguments

 `x` a list of adjacency (symmetric) matrices of undirected graphs. For unweighted graphs, each matrix contains only 0s and 1s. For weighted graphs, each matrix may contains real values that correspond to the weights of the edges. `plot` logical. If TRUE (default) the graph.acf is plotted.

## Value

An object of class acf.

## References

Fujita, A., Takahashi, D. Y., Balardin, J. B., Vidal, M. C. and Sato, J. R. (2017) Correlation between graphs with an application to brain network analysis. _Computational Statistics & Data Analysis_ *109*, 76–92.

## Examples

 ``` 1 2 3 4 5 6 7 8 9 10 11 12 13 14``` ```require(igraph) x <- list() p <- array(0, 100) p[1:3] <- rnorm(3) for (t in 4:100) { p[t] <- 0.5*p[t-3] + rnorm(1) } ma <- max(p) mi <- min(p) p <- (p - mi)/(ma-mi) for (t in 1:100) { x[[t]] <- get.adjacency(erdos.renyi.game(100, p[t])) } graph.acf(x, plot=TRUE) ```

statGraph documentation built on Jan. 11, 2019, 1:06 a.m.