sim.dnetwork: Simulation of the distribution of the network for Breza et...

In ahoundetoungan/PartialNetwork: Estimating Peer Effects Using Partial Network Data

Description

Compute the distribution of the network following McCormick and Zheng (2015) and Breza et al. (2020).

Usage

sim.dnetwork(nu, d, zeta, z)

Arguments

nu	is the vector of gregariousness.
d	is the vector of degrees.
zeta	is a scale parameter that captures the influence of the latent positions on the link probabilities.
z	is a matrix where each row is a spherical coordinate.

Value

a matrix of linking probabilities.

References

Breza, E., Chandrasekhar, A. G., McCormick, T. H., & Pan, M. (2020). Using aggregated relational data to feasibly identify network structure without network data. American Economic Review, Forthcoming https://arxiv.org/abs/1703.04157

McCormick, T. H., & Zheng, T. (2015). Latent surface models for networks using Aggregated Relational Data. Journal of the American Statistical Association, 110(512), 1684-1695. https://www.tandfonline.com/doi/abs/10.1080/01621459.2014.991395.

See Also

sim.network

Examples

N       <- 500 
zeta    <- 1

# Generate the spherical coordinates
z       <- rvMF(N, c(0, 0, 0))

# Genetate the gregariousness
nu      <- rnorm(N, -1.35, 0.37)

# Generate degrees
d       <- runif(N, 0, 45)

dist    <- sim.dnetwork(nu, d, zeta, z)

ahoundetoungan/PartialNetwork documentation built on Oct. 6, 2020, 1:51 a.m.