On Network Autocorrelation Models

This has been an ongoing effort to look at statistical models when the data points are interdependent. It was triggered by work on spatial autocorrelation models that morphed into network autocorrelation models.

  1. Early Work

    • P. Doreian, K. Teuter and C. Wang, “Network Autocorrelation Models: Some Monte Carlo Evidence”, Sociological Methods and Research, Vol. 13, No. 2, 1984, pp. 155-200 Download the Research Paper>
    • R. S. Burt and P. Doreian, “Testing a Structural Model of Perception: Conformity and Deviance with Respect to Journal Norms in Elite Sociological Methodology”, Quality and Quantity, Vol. 16, 1982, pp. 109-150 Download the Research Paper>
    • P. Doreian, “Maximum Likelihood Methods for Linear Models: Spatial Effect and Spatial Disturbance Terms”, Sociological Methods & Research, Vol. 10, No. 3, 1982, pp. 243-269 Download the Research Paper>
    • P. Doreian, “Estimating Linear Models with Spatially Distributed Data”, pp. 359-388 in S. Leinhardt (Ed.), Sociological Methodology 1981, San Francisco: Jossey-Bass, 1981
    • P. Doreian, “Linear Models with Spatially Distributed Data: Spatial Disturbances or Spatial Effects?”, Sociological Methods & Research, Vol. 9, No. 1, Aug. 1980, pp. 29-60 Download the Research Paper>

  2. Later Work

    • Michele La Rocca, Giovanni C. Porzio, Maria Prosperina Vitale and Patrick Doreian, (2017), “Finite sample behaviour of MLE in network autocorrelation models”, Classification, (Big) Data Analysis and Statistical Learning, Mola, Francesco, Conversano, Claudio, Vichi, Maurizio, Eds.), Springer, (forthcoming, 2018) Download the Preprint>
    • Zhang, B., Thomas, A. C., Doreian, P., Krackhardt, D., and Krishnan, R. 2013. Contrasting multiple social network autocorrelations for binary outcomes, with applications to technology adoption. ACM Transactions of Information Systems 3, 4 Article 18 (January 2013) Download the Research Paper>
    • Vitale, M. P, Porzio, G. C. & Doreian, P. (2015) “Examining the effect of social influence on student performance through network autocorrelation models”, Journal of Applied Statistics Download the Research Paper>