growth_l: Identifies growth mechanisms responsible for tie generation in longitudinal networks

Description

This function identifies growth mechanisms responsible for tie generation in longitudinal networks.

Usage

growth_l(net, perspective = "actor", effects, window=NULL, 
binary=FALSE, nstrata=10, seed=NULL, regression=TRUE)

Arguments

net

A longitudinal network

perspective

whether an actor or dyadic perspective should be used (i.e., whether the network is directed or undirected). Currently, only the actor perspective is included.

effects

The effects to be analysed

window

Whether a window should be used.

binary

Whether duplicated ties should be removed.

nstrata

Total number of regression observations for each observed tie (i.e., number of control cases plus 1 for the observed tie). Minimum is 2 in which 1 control case is used for each observed case.

seed

seed for random generator, set to have reproducable results.

regression

Whether R should perform the regression or output a regression table. If you want to run multiple regression, it is quicker to output the table, and then run multiple regressions. By outputting the table, it is also possible to add square terms and additional data.

Value

Returns a regression result or table.

References

Tore Opsahl, Bernie Hogan. Growth mechanisms in continuously-observed networks: Communication in a Facebook-like community. arXiv:1010.2141

Examples

Run this code

# NOT RUN {
## Load sample data
t <- c('2007-09-12 13:45:00', 
'2007-09-12 13:46:31',
'2007-09-12 13:47:54',
'2007-09-12 13:48:21',
'2007-09-12 13:49:27',
'2007-09-12 13:58:14',
'2007-09-12 13:52:17',
'2007-09-12 13:56:59');
i <- c(1,1,2,3,1,3,1,1);
j <- c(2,3,1,2,4,2,3,4);
w <- c(1,1,1,1,1,1,1,1);
sample <- data.frame(t, i, j, w);

## Run the function
growth_l(sample, effects="indegree", nstrata=2)

# }