The effect of density on the level of bias in the network autocorrelation model

Abstract Researchers interested in the effects of social network ties on behavior are increasingly turning to the network autocorrelation model, which allows for the simultaneous computation of individual-level and network-level effects. Earlier research, however, had pointed to the possibility that the maximum likelihood estimates used to compute the network autocorrelation model yielded negatively biased parameter estimates. In this paper we use simulations to examine whether – and the conditions under which – a negative bias exists. We show that the network parameter estimate ρ is negatively biased under nearly all conditions, and that this bias becomes more severe at higher levels of both ρ and network density. We conclude by discussing the implications of these findings for researchers planning to use the network autocorrelation model.

[1]  P. Doreian.  Linear Models with Spatially Distributed Data , 1980 .

[2]  J. Ord,et al.  Spatial Processes: Models and Applications , 1984 .

[3]  Tony E. Smith,et al.  AGGREGATION BIAS IN MAXIMUM LIKELIHOOD ESTIMATION OF SPATIAL AUTOREGRESSIVE PROCESSES , 2001 .

[4]  Luc Anselin,et al.  Some robust approaches to testing and estimation in spatial econometrics , 1990 .

[5]  P. Doreian.  Estimating Linear Models with Spatially Distributed Data , 1981 .

[6]  Tony E. Smith,et al.  Estimation Bias in Spatial Models with Strongly Connected Weight Matrices , 2009 .

[7]  Martina Morris,et al.  Advances in exponential random graph (p*) models , 2007, Soc. Networks.

[8]  Roger Th. A. J. Leenders,et al.  Modeling social influence through network autocorrelation: constructing the weight matrix , 2002, Soc. Networks.

[9]  D. Watts.  Networks, Dynamics, and the Small‐World Phenomenon1 , 1999, American Journal of Sociology.

[10]  Luc Anselin,et al.  Spatial econometrics in practice : A review of software options , 1992 .

[11]  J. LeSage.  Bayesian Estimation of Spatial Autoregressive Models , 1997 .

[12]  Christopher Marquis,et al.  Egocentric, sociocentric, or dyadic?: Identifying the appropriate level of analysis in the study of organizational networks , 2006, Soc. Networks.

[13]  L. Anselin.  Spatial Econometrics: Methods and Models , 1988 .

[14]  K. Ord.  Estimation Methods for Models of Spatial Interaction , 1975 .

[15]  Douglas R. White,et al.  Sexual Division of Labor in African Agriculture: A Network Autocorrelation Analysis , 1981 .

[16]  Douglas R. White,et al.  Network autocorrelation: A simulation study of a foundational problem in regression and survey research , 1982 .

[17]  Christopher Marquis,et al.  Does Network Structure Affect the Size of the Network Effect? The Role of Density in the Network Autocorrelation Model , 2005 .

[18]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[19]  Bernard Fingleton.  Theoretical economic geography and spatial econometrics: bridging the gap between theory and reality , 2004 .

[20]  R. Ralph,et al.  Social Pressures in Informal Groups. , 1951 .