We reformulate regression modeling so that ideas often associated with field theory and social network analysis can be brought to bear at every stage in the computation and interpretation of regression coefficients in studies of organizations. Rather than “transcending” general linear reality, we seek to get more out of it. We formulate a dual to regression modeling based on using the variables to learn about the cases. We illustrate our ideas by applying the new approach to a database of hundreds of violent extremist organizations, focusing on understanding which groups use or pursue unconventional weapons (chemical, biological, radiological, nuclear).
This work was supported by the Defense Threat Reduction Agency, Basic Research Award # HDTRA1-10-1-0017, to the University of Arizona. For helpful comments we thank the reviewers and Elisa Bienenstock, Patrick Doreian, Scott Eliason, James Moody, and Eric Schoon.
Breiger, R. and Melamed, D. (2014), "The Duality of Organizations and their Attributes: Turning Regression Modeling “Inside Out”", Contemporary Perspectives on Organizational Social Networks (Research in the Sociology of Organizations, Vol. 40), Emerald Group Publishing Limited, pp. 263-275. https://doi.org/10.1108/S0733-558X(2014)0000040013Download as .RIS
Emerald Group Publishing Limited
Copyright © 2014 Emerald Group Publishing Limited