cograph (version 2.7.2)

ego_networks: Ego-Network Metrics

Description

Extracts the ego network of each requested node (the node, its neighbors up to a given order, and the ties among them) and reports a tidy table of personal-network metrics: size, internal tie counts and densities, and Burt's structural-hole measures. One row per ego.

Usage

ego_networks(
  x,
  nodes = NULL,
  order = 1,
  mode = c("all", "out", "in"),
  directed = NULL,
  ...
)

Value

A tidy data.frame of class "cograph_ego_networks" with one row per ego and columns:

node

Ego node name.

size

Number of alters (ego-network size, excluding ego).

ego_ties

Number of edges in the ego network (ego + alters).

ego_density

Edge density of the ego network including ego.

alter_ties

Number of edges among the alters only (excluding ego).

alter_density

Edge density among the alters. Low values indicate many structural holes / brokerage opportunities.

effective_size

Burt's effective size of the ego network (order = 1 only).

constraint

Burt's constraint (order = 1 only).

Arguments

x

Network input: matrix, igraph, network, cograph_network, or tna object.

nodes

Character vector of node names or integer vector of node indices selecting which egos to report. NULL (default) uses every node.

order

Integer neighborhood order defining the ego network. 1 (default) is the standard ego network (ego + direct neighbors). Burt's effective_size and constraint are only defined for order = 1 and are returned as NA otherwise.

mode

For directed networks, which ties define the neighborhood: "all" (default), "out", or "in".

directed

Logical or NULL. If NULL (default), auto-detect from matrix symmetry.

...

Currently unused; directed is already an explicit argument above and to_igraph accepts no others.

Details

effective_size and constraint are computed on the full network (Burt's measures are defined directly from each node's order-1 ego network), reusing the same implementations as centrality so results match centrality(x, measures = c("effective_size", "constraint")).

References

Burt, R.S. (1992). Structural Holes: The Social Structure of Competition. Harvard University Press.

See Also

centrality (for effective_size, constraint, dispersion), select_neighbors, neighborhood_overlap

Examples

adj <- matrix(c(
  0, 1, 1, 0, 0,
  1, 0, 1, 0, 0,
  1, 1, 0, 1, 1,
  0, 0, 1, 0, 1,
  0, 0, 1, 1, 0
), 5, 5, byrow = TRUE)
rownames(adj) <- colnames(adj) <- LETTERS[1:5]
cograph::ego_networks(adj)