Research
How it all comes together: Integrated statement
I study the social structures of organizations and systems. How do the structures evolve, how do they affect what an organization does? I often use quantitative methods drawing on social networks and multilevel models . Typically I study small systems, in particular schools as organizations, a topic that is part of the sociology of education. Recently I've been working with the Add Health data.
Causal Inference and Robustness Indices
Frank, K.
2000. "Impact of a Confounding Variable on the Inference of a
Regression Coefficient."
Sociological Methods and Research, 29(2), 147-194
When one reports a regression from an observational study, there is always the concern: "But have you controlled for xxx?" In this article, I index the impact of a confounding variable in terms of the product of two correlations (correlation between the confounding variable and the predictor of interest X correlation between the confounding variable and the outcome -- see figure below). This product appears in both the estimate of a regression coefficient and its standard error. Thus it can be used to quantify the impact necessary to alter a statistical inference. In the article I develop the index for the bivariate and multivariate contexts, compare it to other statistics, apply to an example, describe a reference distribution, and then interpret in the context of recent concerns about causal and statistical inferences.
The Impact of a Confounding Variable on a Regression Coefficient
Frank, K.A. (2005).
"Teacher Networks" Entry for Encylopedia of Schools, edited by Kathryn Borman.
Frank,
K.A., Mueller, K., Krause, A. and Taylor, W. (2005). "The Intersection of Global Trade, Social Networks, and Fisheries."
To be published in a book by Cambridge Press, edited by
see also
Pan, W., and Frank, K.A. (2004). "An Approximation to the Distribution
of the Product of Two Dependent Correlation Coefficients." Journal of
Statistical Computation and Simulation, 74, 419-443
Pan, W., and Frank, K.A., 2004.
"A probability index of the robustness of a causal inference," Journal
of Educational and Behavioral Statistics, 28, 315-337.
spreadsheet for calculating indices
sas program for calculating indices and related measures
Representation of Social Structure
I have analyzed the social networks of teachers in a school, and how that links to teachers' background characteristics and their orientations to teaching {see the figure below}. For related articles, see:
Frank. K.A. 1995. Identifying Cohesive Subgroups. Social Networks (17): 27-56
Frank, K. A. and Yasumoto, J. 1996. "Embedding Subgroups in the Sociogram: Linking Theory and Image". Connections 19 (1): 43-57 .
Regarding the above figure, in Frank, K. A. (1998). "The Social Context of Schooling: Quantitative Methods" Review of Research in Education, Vol, 23, chapter 5, pages 171-216.
I wrote:
The figure establishes a basis for integrating
qualitative data and information from survey instruments to characterize the processes through which teachers are affected by their social contexts. As indicated in school documents, at "Our Hamilton High," the student population has become increasingly disadvantaged over the years, as poor families have moved to the district from a nearby city and as the children of the more established wealthier families have aged. The teachers have responded in various ways to this exogenous change. Some who had difficulty adapting to the change sought early retirement. Others altered their mode of relating to thestudents, befriending the students whom they felt were most in need. In this sense the school is like others described by (Grant, 1988) and (Metz, 1990). A core of teachers relate to the new types of students by acting as "moral agents," inculcating students into a specific set of values emphasizing citizenship and responsibility by keeping firm control of the classroom and through personal example (see Bidwell, et al., 1997, for a definition and operationalization of moral agency in terms of responses to survey items, reliability=.74).
By assigning the teachers' id numbers in the sociogram to represent their emphasis on moral agency (the lower the number the higher the rank on moral agency), I used the image in Figure 4 as a basis for inferring processes through which teachers influenced one another (Frank, 1996). To begin, moral agency is cultivated within subgroup A as the members of subgroup A engage in discussions with one another on a near daily basis (as indicated by the thick lines within the boundary of subgroup A and as observed during field work). Once a week or month one of the teachers in subgroup A engages in discussions with a teacher outside the subgroup (as indicated by the thinner lines between members of subgroup A and members of other subgroups), thus possibly influencing the member of the other subgroup. The effect of these discussions is critical to integrating the subgroups into the totality of the organization, as opinions, information, etc. that accumulate in each subgroup during daily discussions are transmitted to the other subgroup. Therefore even teachers who do not adopt moral agency in direct response to changes in the student population may be affected, through direct and indirect discussions, by the orientations of the teachers in subgroup A.
Though others have observed the processes through which teachers socialize one another on a dyadic level (Fuller & Izu 1986; Grant, 1988; Hanson, 1978; Lightfoot, 1983; Metz, 1990; Rosenholtz & Simpson, 1990), Figure 4 represents the structure through which the socialization process occurs at the level of the school. Therefore I was able to describe moral agency as being cultivated within subgroup A and then spreading to other subgroups where it encounters competing orientations. Of course, this process could be described with an alternative orientation being cultivated in another subgroup and then moving to the members of subgroup A. Indeed the image in Figure 4 suggests an equilibrium of the system, with those in subgroup C who are mixed and moderate in their orientations mediating between the competing orientations of those at the top and bottom. Thus the image in Figure 4 represents how processes within one subgroup may generate aspects of the organizational culture that then affects all people in the school.
Adolescent Social Contexts in Schools
I am part of the AHAA project that supplements the Add Health Data base with information from high school student transcripts. With Sam Field, I adapated my clustering algorithm to two-mode data (e.g., students and courses)
*Field,
S. *Frank, K.A., Schiller, K, Riegle-Crumb, C, and Muller, C. (in
press) "Identifying Social Contexts in Affiliation Networks:
Preserving the Duality of People and Events. Social Networks
* coequal first authorship
Social Factors and Implementation of Innvations in Organizations
Frank, K.A. (2005). "Teacher Networks" Entry for Encylopedia of Schools, edited by Kathryn Borman.
Chaos and Complexity in Organizations
Kyle Fahrbach and I modeled how people influence one another and choose with whom to interact. The combination of these processes can generate a range of equilibria characteristic of the complex system of organizational culture. See
Myazaki, Yasuo and Frank, K.A. (2005). "A Hierarchical Model with Factor Analysis Structure at Level 2" Journal of Educational and Behavioral Statistics
Herman, S.E., Frank, K.A., Mowbray, C.T., Ribisl, K.M., Davidson, W.S., Bootsmiller, B., Jordan, L., Greenfield, A.L., Loveland, D., Luke, D. A. 2000. "Longitudinal Effects of Integrated Treatment on Alcohol Use for Persons with Mental Illness and Substance Use Disorders." Journal of Behavioral Health Services and Research. 27 (3), 286-302.
Frank, K.A. and Yasumoto, J. 1998. "Linking Action to Social Structure within a System: Social Capital Within and Between Subgroups." American Journal of Sociology 104 (3): 642-686. (see Jstor)
Frank, K. A. 1998. "The Social Context of Schooling: Quantitative Methods". Review of Research in Education 23, chapter 5: 171-216.
Bidwell, C. E., Frank, K.A., and Quiroz, P. 1997. "Teacher Types, Workplace Controls, and the Organization of Schools." Sociology of Education, 70 (4): 285-307. (see Jstor)
Seltzer, M. H., Frank, K.A., & Bryk, A.S. 1994. "The Metric Matters: The Sensitivity of Conclusions Concerning Growth in Student Achievement to Choice of Metric." Educational Evaluation and Policy Analysis 16 (1): 41-49.
Frank, K.A. 1993. Identifying Cohesive Subgroups. Unpublished Doctoral Dissertation, University of Chicago.
Bryk, A.S. & Frank, K.A. 1991. "The Specialization of Teachers' Work: An Initial Exploration." In Schools, Classrooms, and Pupils, edited by S.W. Raudenbush, S. W., and J.D. Willms. New York: Academic Press (Harcourt Brace Jovanovich).
With multiple coauthors from Fisheries and Wildlife, I have written about how human networks are at the intersection of global networks and the neworks of ecosystems
