Locally Aggregated Structures (LAS)

Generates LAS matrices using different criteria as described in Krackhardt (1990).

las(M, ..., rule, threshold = 0.5)

LAS(M, ..., rule, threshold = 0.5)

# S3 method for list
las(M, ..., rule, threshold = 0.5)

# S3 method for matrix
las(M, ..., rule, threshold = 0.5)

Arguments

M	Either a list of matrices of size n (need not to be square), or a single matrix of size n (see details).
...	More matrices to be passed to the function.
rule	Character. Rule used to create the LAS matrix. Can be any of "intersection", "union", or "threshold" (see the Rule section).
threshold	Number of minimum agreements to set the tie to 1. This is used for the case when rule = "threshold".

Rule

When rule = "interesection" or rule = "i", the intersection method is used. A tie is marked as present iff both i and j agree on the existance if (i,j).

When rule = "union" or rule = "u", the union method is used. In such case a tie is marked as present if any of the individuals declares it.

When rule = "threshold" or rule = "t", the threshold method is used in which a tie is marked as present iff the proportion of individuals who agree on the existance of that is greater than threshold. In its paper, Krackhardt calls this Concensus Structure (CS).

References

Krackhardt, D. (1987). Cognitive social structures. Social networks, 9(2), 109-134.

Examples

data(powerset03)
x <- powerset03[1:3]

# It only exists if i and j declare it
las(x, rule="i")
#>      [,1] [,2] [,3]
#> [1,]    0    0    0
#> [2,]    1    0    0
#> [3,]    0    0    0

# Same as above
las(x[[1]], x[[2]], x[[3]], rule="i")
#>      [,1] [,2] [,3]
#> [1,]    0    0    0
#> [2,]    1    0    0
#> [3,]    0    0    0

# It exists if either i or j declare it
las(x, rule="u")
#>      [,1] [,2] [,3]
#> [1,]    0    0    0
#> [2,]    1    0    0
#> [3,]    1    0    0

# Not enough agreement
las(x, rule="t", threshold=.9)
#>      [,1] [,2] [,3]
#> [1,]    0    0    0
#> [2,]    0    0    0
#> [3,]    0    0    0