Groupings, Networks, and Clusters
While much descriptive work relies heavily on central tendencies and variation, other analytical
methods are emerging to identify and explore more recently observed phenomena, such as networks,
clustering, and other interactions within education organizations and interpersonal relationships.
In the context of education, peer networks sometimes refer to the phenomenon of students inter-
acting with other students to attain education goals.
34
For example, peer groups of students may tend
to organize themselves into certain course-taking patterns.
35
Clusters, on the other hand, are groups
of units (such as students, teachers, classrooms, or schools) not that interact with each other but that
have similar traits. Members of a cluster share multiple characteristics, such as personality traits or
learning behaviors, which distinguish them from other clusters.
36
Network analysis and cluster analysis are two common approaches for studying grouping phenom-
ena (see Box 11). Network analysis describes systems of links among people or other subjects of
study, whereas cluster analysis describes sets of actors with the same characteristics, whether they are
courses or behavioral indexes.
37
Descriptive analysis can contribute to the identification and depic-
tion of these types of patterns from within large sets of data that measure individual dynamics and
interactions.
38
Once better understood, such complex social and organizational patterns may shed
light on the emergence of skill gaps and other achievement outcomes, as well as on possible points
for productive interventions in the social and interpersonal associations of students and other indi-
viduals in a classroom or school setting.
Box 11. Example of Descriptive Research that Uses Network and Cluster Analysis as Descriptive Tools
Daly, A. J., & Finnigan, K. (2011). The ebb and flow of social network ties between district leaders under high
stakes accountability. American Education Research Journal, 48(1): 39–79.
This study examined the underlying social networks of a district leadership team engaged in systemic reform
efforts in response to multiple schools being designated as “in need of improvement” under the No Child Left
Behind (NCLB) Act of 2001. Using a survey to collect data on social networking relationships between central
office administrators and school building leaders, the researchers developed a longitudinal case study focused
34
O'Donnell, A. M., & King, A. (1999).
Cognitive perspectives on peer l e arning
. New York: Routledge.
35
McFarland, D. A. (2006). Curricular flows: Trajectories, turning points, and assignment criteria in high school
math careers.
Sociolog y of Education, 79
(3): 177–205.
36
See, as examples, for more information on network analysis: Kadushin, C. (2012).
Un derstanding social
networks
. Oxford, UK: Oxford University Press; Knoke, D., & Yang, S. (2008).
Social network analysis,
2nd ed.
Los Angeles: Sage Publications; Prell, C. (2011).
Social network analysis : Hist ory, theory and metho d o log y ,
3rd
ed. Los Angeles: Sage Publications; Scott, J. (2012).
Social network analysis
. Los Angeles: Sage Publications; and
Wasserman, S., & Faust, K. (1994).
Social network analysis: Methods a n d applications
. Cambridge, UK:
Cambridge University Press. See, as examples, for more information on cluster analysis: Aldenderfer, M. S., &
Blashfield, R. K. (1984).
Cluster analysis
(Quantitative Applications in the Social Sciences). Los Angeles: Sage
Publications; Everitt, B. S., Landau, S., Leese, M., & Stahl, D. (2011).
Cluster analysi s,
5th ed. New York: Wiley;
and King, R. S. (2014).
Cluster analysis and data mining: An introduction
. Dulles, VA: Mercury Learning &
Information.
37
Wasserman, S., & Faust, K. (1994).
Social network analysis: Methods a n d applications
. Cambridge, UK:
Cambridge University Press.
38
Rawlings, C. M., & McFarland, D. A. (2010). Influence flows in the academy: Using affiliation networks to
assess peer effects among researchers.
Social Science Research, 40
(3): 1001–1017.
25