Much of the information in this post has been a conceptual understanding from the book “Doing Social Network Research” by Dr. Garry Robins. Social Network Analysis (SNA) as a methodology requires its own way of thinking. As a social science researcher, who uses SNA, one must be willing to step-out of their comfort zone to examine social contexts and social phenomena in a different way. This way of thinking is important to understand from a SNA philosophical perspective. A philosophical perspective is the lens in which a researcher understands reality and creates new knowledge. Specifically, a SNA perspective is applied to the way researchers examine a social system of connections.The ontology (knowledge) through this perspective examines the network relationships and also the social actors who have intentionality differs from traditional social science research in the sense that individuals are all tied together with the assumption of complex structures among the variables that are studied (Robins, 2015).
To perform systematic inquiry, the research questions asked as researchers should guide the study and the statistical procedures used for data analysis. SNA differs from traditional social science research designs from the questions asked which impacts the structure of the data during analysis. Most social science research involves linear models or the utilization of randomized control experimental settings to look for group differences. Observations in these designs are all assumed to be independent from one another. Hence, the overall conceptual framework in which is used to organize a research study using SNA may be foreign to some social science researchers who have not been trained in performing SNA specifically. Robin (2015) encompasses this idea perfectly when stating, “Networks are based on connectivity not atomization. Networks are structured and patterned, not summed and averaged. Yet, this is more than a methodological nuisance denying us the comfort of standard statistics and classic research designs. It is the heart of a network theorization and we need to adapt to its demands, rather than try to contort network research back into a more familiar shape” (p.10).
As mentioned above, traditional social science research designs are of a linear model or even way of thinking. Data from these designs are usually statistical analyses portrayed in statistical tables carried about by a linear thinking conceptual model. When utilizing SNA social scientists must be able to abstract the observed social systems which should be heavily influenced by theory, finding the best way to explain the social elements on a social network graph is not a linear process.
Relational data explains the difference contents of social connections, which could be many things pertaining to just one relationship. The data is pretty much the variable relations being examined for, example collaboration among co-workers, information flows, or who is communicating with who are all examples of relational data. The relational data describes who the actors are, what types of tie to the study, what are the relevant outcomes and at what level which are all theoretical decisions and conclusions drawn from the data which ultimately makes traditional social science designs like predictive analysis difficult to address.