PartialNetwork-package: The PartialNetwork package

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

The PartialNetwork package

Description

The PartialNetwork package implements instrumental variables (IV) and Bayesian estimators for the linear-in-mean SAR model (e.g. Bramoulle et al., 2009) when the distribution of the network is available, but not the network itself. To make the computations faster PartialNetwork uses C++ through the Rcpp package (Eddelbuettel et al., 2011).

Details

Two main functions are provided to estimate the linear-in-mean SAR model using only the distribution of the network. The function sim.IV generates valid instruments using the distribution of the network (see Propositions 1 and 2 in Boucher and Houndetoungan (2020)). Once the instruments are constructed, one can estimate the model using standard IV estimators. We recommend the function ivreg from the package AER (Kleiber et al., 2020). The function mcmcSAR performs a Bayesian estimation based on an adaptive MCMC (Atchade and Rosenthal, 2005). In that case, the distribution of the network acts as prior distribution for the network.
The package PartialNetwork also implements a network formation model based on Aggregate Relational Data (McCormick and Zheng, 2015; Breza et al., 2017). This part of the package relies on the functions rvMF, dvMF and logCpvMF partly implemented in C++, but using code from movMF (Hornik and Grun, 2014).

Author(s)

Maintainer: Elysee Aristide Houndetoungan [e-mail]

Authors:

• Vincent Boucher [e-mail]

References

Atchade, Y. F., & Rosenthal, J. S., 2005, On adaptive markov chain monte carlo algorithms, Bernoulli, 11(5), 815-828, doi: 10.3150/bj/1130077595.

Boucher, V., & Houndetoungan, A., 2022, Estimating peer effects using partial network data, Centre de recherche sur les risques les enjeux economiques et les politiques publiques, https://ahoundetoungan.com/files/Papers/PartialNetwork.pdf.

Bramoulle, Y., Djebbari, H., & Fortin, B., 2009, Identification of peer effects through social networks, Journal of econometrics, 150(1), 41-55, doi: 10.1016/j.jeconom.2008.12.021.

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, 110(8), 2454-84, doi: 10.1257/aer.20170861

Eddelbuettel, D., Francois, R., Allaire, J., Ushey, K., Kou, Q., Russel, N., ... & Bates, D., 2011, Rcpp: Seamless R and C++ integration, Journal of Statistical Software, 40(8), 1-18, doi: 10.18637/jss.v040.i08

Lee, L. F., 2004, Asymptotic distributions of quasi-maximum likelihood estimators for spatial autoregressive models. Econometrica, 72(6), 1899-1925, https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1468-0262.2004.00558.x

LeSage, J. P. 1997, Bayesian estimation of spatial autoregressive models, International regional science review, 20(1-2), 113-129, https://journals.sagepub.com/doi/10.1177/016001769702000107.

Mardia, K. V., 2014, Statistics of directional data, Academic press.

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, doi: 10.1080/01621459.2014.991395.

Wood, A. T., 1994, Simulation of the von Mises Fisher distribution. Communications in statistics-simulation and computation, 23(1), 157-164. doi: 10.1080/03610919408813161.

See Also

Useful links:

• https://github.com/ahoundetoungan/PartialNetwork

• Report bugs at https://github.com/ahoundetoungan/PartialNetwork/issues

ahoundetoungan/PartialNetwork documentation built on Feb. 8, 2023, 9:27 p.m.