Abstract
This study proposes a novel polynomial network autoregressive model by incorporating higher-order connected relationships to simultaneously model the effects of both direct and indirect connections. A quasi-maximum likelihood estimation method is proposed to estimate the unknown influence parameters, and demonstrates its consistency and asymptotic normality without imposing any distribution assumption. Moreover, an extended Bayesian information criterion is set for order selection with a divergent upper order. The application of the proposed polynomial network autoregressive model is demonstrated through both the simulation and the real data analysis.
Similar content being viewed by others
References
Chen J H, Chen Z H. Extended Bayesian information criteria for model selection with large model spaces. Biometrika, 2008, 95: 759–771
Chen J H, Chen Z H. Extended BIC for small-n-large-P sparse GLM. Statist Sinica, 2012: 555–574
Chen X L, Chen Y X, Xiao P. The impact of sampling and network topology on the estimation of social intercorrelations. J Mark Res, 2013, 50: 95–110
Clauset A, Shalizi C R, Newman M E J. Power-law distributions in empirical data. SIAM Rev, 2009, 51: 661–703
Cohen-Cole E, Liu X D, Zenou Y. Multivariate choices and identification of social interactions. J Appl Econometrics, 2018, 33: 165–178
Erdös P, Rényi A. On random graphs I. Publ Math Debrecen, 1959, 6: 290–297
Fan J Q, Li R Z. Variable selection via nonconcave penalized likelihood and its oracle properties. J Amer Statist Assoc, 2001, 96: 1348–1360
Farber S, Páez A, Volz E. Topology and dependency tests in spatial and network autoregressive models. Geograph Anal, 2009, 41: 158–180
Fracassi C. Corporate finance policies and social networks. Management Sci, 2017, 63: 2420–2438
Goetzke F. Network effects in public transit use: Evidence from a spatially autoregressive mode choice model for New York. Urban Stud, 2008, 45: 407–417
Gupta A, Robinson P M. Inference on higher-order spatial autoregressive models with increasingly many parameters. J Econometrics, 2015, 186: 19–31
Gupta A, Robinson P M. Pseudo maximum likelihood estimation of spatial autoregressive models with increasing dimension. J Econometrics, 2018, 202: 92–107
Huang D Y, Lan W, Zhang H H, et al. Least squares estimation of spatial autoregressive models for large-scale social networks. Electron J Stat, 2019, 13: 1135–1165
Huang D Y, Wang F F, Zhu X N, et al. Two-mode network autoregressive model for large-scale networks. J Econometrics, 2020, 216: 203–219
Lan W, Fang Z, Wang H S, et al. Covariance matrix estimation via network structure. J Bus Econom Statist, 2018, 36: 359–369
Lee L F. Asymptotic distributions of quasi-maximum likelihood estimators for spatial autoregressive models. Econometrica, 2004, 72: 1899–1925
Lee L F, Liu X D. Efficient GMM estimation of high order spatial autoregressive models with autoregressive disturbances. Econometric Theory, 2010, 26: 187–230
LeSage J P. An introduction to spatial econometrics. Rev Econom Indust, 2008, 123: 19–44
LeSage J P. Spatial Econometrics. Cheltenham: Edward Elgar, 2015
Lin X, Weinberg B A. Unrequited friendship? How reciprocity mediates adolescent peer effects. Regional Sci Urban Econom, 2014, 48: 144–153
Liu X D, Patacchini E, Zenou Y. Endogenous peer effects: Local aggregate or local average? J Econom Behav Organiz, 2014, 103: 39–59
Luo S, Chen Z H. Selection consistency of EBIC for GLIM with non-canonical links and diverging number of parameters. Stat Interface, 2013, 6: 275–284
Nowicki K, Snijders T A B. Estimation and prediction for stochastic blockstructures. J Amer Statist Assoc, 2001, 96: 1077–1087
Ozsoylev H N, Walden J, Yavuz M D, et al. Investor networks in the stock market. Rev Financ Stud, 2014, 27: 1323–1366
Pace R K, Barry R. Quick computation of spatial autoregressive estimators. Geograph Anal, 1997, 29: 232–247
Peng S C, Yang A M, Cao L H, et al. Social influence modeling using information theory in mobile social networks. Inform Sci, 2017, 379: 146–159
Seber G A F. A Matrix Handbook for Statisticians. New York: John Wiley & Sons, 2008
Zhang X, Pan R, Guan G Y, et al. Logistic regression with network structure. Statist Sinica, 2020, 30: 673–693
Zhou J, Tu Y D, Chen Y X, et al. Estimating spatial autocorrelation with sampled network data. J Bus Econom Statist, 2017, 35: 130–138
Zhu X, Huang D Y, Pan R, et al. Multivariate spatial autoregressive model for large scale social networks. J Econometrics, 2020, 215: 591–606
Zou T, Luo R, Lan W, et al. Network influence analysis. Statist Sinica, 2021, 31: 1727–1748
Acknowledgements
The first author was supported by the Fundamental Research Funds for the Central Universities (Grant No. JBK2207075). The second author was supported by National Natural Science Foundation of China (Grant Nos. 71991472, 12171395, 11931014 and 71532001), the Joint Lab of Data Science and Business Intelligence at Southwestern University of Finance and Economics and the Fundamental Research Funds for the Central Universities (Grant No. JBK1806002). The fourth author was supported by the Humanity and Social Science Youth Foundation of Ministry of Education of China (Grant No. 19YJC790204). The authors are grateful to the referees for their insightful comments and constructive suggestions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lei, B., Lan, W., Fang, N. et al. Polynomial network autoregressive models with divergent orders. Sci. China Math. 66, 1073–1086 (2023). https://doi.org/10.1007/s11425-021-1978-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11425-021-1978-7
Keywords
- diverging order
- extended Bayesian information criterion
- polynomial network autoregressive model
- quasi-maximum likelihood estimation