A fundamental task in data analysis is understanding the differences between several con-trasting groups. These groups can represent different classes of objects, such as male or female students, or the same group over time, e.g. freshman students in 1993 through 1998. We present the problem of mining contrast sets: conjunctions of attributes and values that differ meaningfully in their distribution across groups. We provide a search algorithm for mining contrast sets with pruning rules that drastically reduce the computational complexity. Once the contrast sets are found, we post-process the results to present a subset that are surprising to the user given what we have already shown. We explicitly control the probability of Type I error (false positives) and guarantee a maximum error rate for the entire analysis by using Bonferroni corrections.

Abstract not found

Research article

This chapter explores the role end user perceptions in information technology adoption from the perspective of innovation diffusion theory. It is based on empirical data from a three-year longitudinal study of an information system implementation in an engineering organization. Data were collected on six different applications and their adoption by four categories of end users: engineering managers, project engineers, professionals, and secretaries. The data indicate a substantial variance across time, user categories, and applications in terms of adoption rates and perceptions of technology. The managerial implications of the results are that differentiated implementation strategies focused on specific end user categories are likely to be more successful than a single broadbrush strategy for all users. The results also suggest a framework for predicting technology adoption in the long run, based on initial adoption rates and user perceptions of technology.

This article discusses the Juvenile Justice Educational Enhancement Program’s evaluation of juvenile justice education through the integration of multiple data sources. Validation of best practices and the corresponding effect of these practices on community reintegration require the development of a comprehensive database of program-level and individual-level indicators from several sources. These sources include the Florida Department of Education, the Florida Department of Juvenile Justice, the Florida Department of Law Enforcement, the Florida Department of Corrections, and the Juvenile Justice Educational Enhancement Program’s own educational quality assurance and pre-/posttest data. This article examines the methodological, political, and bureaucratic obstacles encountered in this effort. Evaluation research analyses are also explored with an emphasis on the meaning of outcome measures relative to causal issues of time order, the modeling of events, and analytic strategy. The article provides a framework for future juvenile justice educational evaluation and a critical examination of problems encountered in integrating data sources for the purpose of outcome evaluation.

The author(s) shown below used Federal funds provided by the U.S. Department of Justice and prepared the following final report: