Estimation of Parameter-Dependent Network Centrality Measures

Provides methods for estimating parameter-dependent network centrality measures with linear-in-means models. Both non linear least squares and maximum likelihood estimators are implemented. The methods allow for both link and node heterogeneity in network effects, endogenous network formation and the presence of unconnected nodes. The routines also compare the explanatory power of parameter-dependent network centrality measures with those of standard measures of network centrality. Benefits and features of the 'econet' package are illustrated using data from Battaglini and Patacchini (2018), which examine the determinants of US campaign contributions when legislators care about the behavior of other legislators to whom they are socially connected. For additional details, see the vignette.


econet

The R package econet provides methods for estimating parameter-dependent network centrality measures with linear-in-means models. Both non linear least squares and maximum likelihood estimators are implemented. The methods allow for both link and node heterogeneity in network effects, endogenous network formation and the presence of unconnected nodes. The routines also compare the explanatory power of parameter-dependent network centrality measures with those of standard measures of network centrality. Benefits and features of the econet package are illustrated in the vignette of the package.

Implementing Econet

econet provides four functions. The first one is net_dep, which allows one to estimate a model of social interactions and compute the relative weighted Katz-Bonacich centralities of the agents. Different behavioral models can be chosen (see section 4 of the vignette for details). Moreover, the hypothesis of homogenous or heterogenous spillovers can be tested. The second function is boot, which is built to obtain valid inference when the NLLS estimator with Heckman correction is used. The third function is horse_race, which allows one to compare the explanatory power of parameter-dependent centralities relative to other centrality measures. The forth function is quantify, and it is used to assess the effect of control variables in the framework designed by BLP.

The package has at least four merits.

First, it complements the R packages implementing traditional centrality measures for binary networks, igraph and sna, and weighted networks, tnet, by introducing new eigensolutions-based techniques to rank agents' centrality. Second, whereas previous packages, such as btergm, hergm, the statnet suite, and xergm, created environments for modeling the statistical processes underlying network formation, econet provides the first framework to investigate the socio-economic processes operating on networks (i.e. peer effects). Third, it completes the collection of functions for modeling spatial dependence in cross-sectional data provided by spdep and splm, by allowing the users to: i) consider the presence of unconnected nodes, and ii) address network endogeneity. Finally, it equips the R archive with routines still unavailable in other commonly used software for the investigation of relational data, such as Matlab, Pajek, Python and Stata.

The examples we use to showcase the functionality of econet are contained in the vignette.

News

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("econet")

0.1.81 by Valerio Leone Sciabolazza, a year ago


Browse source code at https://github.com/cran/econet


Authors: Marco Battaglini [aut] , Valerio Leone Sciabolazza [aut, cre] , Eleonora Patacchini [aut] , Sida Peng [aut]


Documentation:   PDF Manual  


MIT + file LICENSE license


Imports bbmle, igraph, intergraph, Matrix, MASS, minpack.lm, sna, spatstat.utils, stats, tnet, utils, plyr, dplyr

Suggests testthat, R.rsp


See at CRAN