partition {SyNet} | R Documentation |
Tests the capability of a sympatry network to contain units of co-occurrence.
partition(iptsymp, replica = 1)
iptsymp |
Matrix object. It must be binary (1/0) and symmetric. |
replica |
Number of random matrices to be produced. |
The input argument iptsymp
corresponds to any adjacency matrix that
reflects the incidence (1) or not (0) of a sympatric link between pairs of
species.
Random matrices are generated according to a Bernoulli model. A random number between 0 and 1 is generated for each pair of species or cell. If this number is lower than the density of the network associated to the observed matrix, a 1 score is assigned.
The statisitc corresponds to the Partition Index (PI). The test counts the number of random matrices that yields a PI value higher or equal to the observed one.
If replica
> 1, a list is generated with the following components:
$Input |
Sympatry matrix observed. |
$ProbTie |
Density of network associated to. |
$NodeNr |
Number of nodes considered. |
$PIobserved |
Observed Partition Index. |
$PIrandomized |
Statistical summary of randomized Partition Index. |
$ProbTie |
Fraction of replica where the randomized Partition
Index is >= the observed one. |
If replica
= 1, the Partition Index of the observed matrix is calculated.
Daniel A. Dos Santos
Dos Santos, D.A., Fernandez, H.R., Cuezzo, M.G., Dominguez, E. Sympatry Inference and Network Analysis in Biogeography. Systematic Biology (in press).
The statistic PI is calculated by the function Partition_Index
data(epiphragmophora) p <- dotinfer(epiphragmophora) partition(p[[1]], 100)