Nonparametric identification in index models of link formation

DOI10.1016/J.JECONOM.2019.09.005zbMATH Open1456.62284arXiv1710.11230OpenAlexW2980531765WikidataQ127030121 ScholiaQ127030121MaRDI QIDQ2182134FDOQ2182134

Authors: Wayne Yuan Gao 

Publication date: 21 May 2020

Published in: Journal of Econometrics (Search for Journal in Brave)

Abstract: We consider an index model of dyadic link formation with a homophily effect index and a degree heterogeneity index. We provide nonparametric identification results in a single large network setting for the potentially nonparametric homophily effect function, the realizations of unobserved individual fixed effects and the unknown distribution of idiosyncratic pairwise shocks, up to normalization, for each possible true value of the unknown parameters. We propose a novel form of scale normalization on an arbitrary interquantile range, which is not only theoretically robust but also proves particularly convenient for the identification analysis, as quantiles provide direct linkages between the observable conditional probabilities and the unknown index values. We then use an inductive "in-fill and out-expansion" algorithm to establish our main results, and consider extensions to more general settings that allow nonseparable dependence between homophily and degree heterogeneity, as well as certain extents of network sparsity and weaker assumptions on the support of unobserved heterogeneity. As a byproduct, we also propose a concept called "modeling equivalence" as a refinement of "observational equivalence", and use it to provide a formal discussion about normalization, identification and their interplay with counterfactuals.

Full work available at URL: https://arxiv.org/abs/1710.11230

Recommendations

• An econometric model of network formation with degree heterogeneity
• Identification of nonparametric simultaneous equations models with a residual index structure
• scientific article; zbMATH DE number 1136442
• Identification and Estimation of a Partially Linear Regression Model Using Network Data
• Identification and estimation of linear social interaction models

zbMATH Keywords

nonparametric identificationnetwork formationhomophilyinterquantile rangedegree heterogeneity

Mathematics Subject Classification ID

Applications of statistics to economics (62P20) Random graphs (graph-theoretic aspects) (05C80) Social networks; opinion dynamics (91D30)

Cites Work

• Semiparametric analysis of discrete response. Asymptotic properties of the maximum score estimator
• Maximum score estimation of the stochastic utility model of choice
• An Exponential Family of Probability Distributions for Directed Graphs
• Title not available (Why is that?)
• Semiparametric Analysis of Random Effects Linear Models from Binary Panel Data
• Multiple fixed effects in binary response panel data models
• Random graphs with a given degree sequence
• Identification of nonseparable models using instruments with small support
• A central limit theorem in the \(\beta \)-model for undirected random graphs with a diverging number of vertices
• A sequential importance sampling algorithm for generating random graphs with prescribed degrees
• A structural model of dense network formation
• A weak law for moments of pairwise stable networks
• Identifying Preferences in Networks With Bounded Degree
• Asymptotics in directed exponential random graph models with an increasing bi-degree sequence
• An econometric model of network formation with degree heterogeneity
• Discretizing unobserved heterogeneity

Cited In (4)

• Logical differencing in dyadic network formation models with nontransferable utilities
• Network and panel quantile effects via distribution regression
• Identification and inference of network formation games with misclassified links
• Nonparametric Identification in the Dynamic Stochastic Block Model

This page was built for publication: Nonparametric identification in index models of link formation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2182134)