1. Taming Multivariate Data: Conceptual and Methodological Issues
- Author
-
Redlinger, Lawrence J., Wiorkowski, John J., and Moses, Anna I.
- Abstract
The purpose of this chapter is to discuss the conceptual, methodological, and statistical challenges in selecting appropriate peer institutions for comparative purposes. The authors' approach embraces a Western scientific tradition that physical things and phenomena can be "reduced into a set of key variables--identifiable parts--that make key contributions, and that the behavior of the whole--in this case institutions of higher education--can be understood by knowing the parts and how they contribute (behave)." Furthermore, a value is placed on "efficiency" and "effective (successful) outcomes." These assumptions have spawned a number of models that stress in varying degrees the larger environmental, "structural and/or contextual variables and 'inputs-processes-outputs.'" Input-processes-outputs models are central to comparative analyses in general and benchmarking in particular. A representation of a general benchmarking model is provided. This point of view frames the conceptual and methodological issues and the technique of principal components analysis the authors discuss in this chapter. (Contains 4 tables, 6 figures, and 4 notes.)
- Published
- 2012
- Full Text
- View/download PDF