Volume 2 Number 2
1999
You will need a free Acrobat PDF format reader to read these articles.
Click here for information.

33-43

Data Quality in Linear Regression Models: Effect of Errors in Test Data and Errors in Training Data on Predictive Accuracy

Barbara D. Klein & Donald F. Rossin
University of MIchigan-Dearborn USA

Although databases used in many organizations have been found to contain errors, little is known about the effect of these errors on predictions made by linear regression models. The paper uses a real-world example, the prediction of the net asset values of mutual funds, to investigate the effect of data quality on linear regression models. The results of two experiments are reported.  The first experiment shows that the error rate and magnitude of error in data used in model prediction negatively affect the predictive accuracy of linear regression models. The second experiment shows that the error rate and the magnitude of error in data used to build the model positively affect the predictive accuracy of linear regression models. All findings are statistically significant. The findings have managerial implications for users and builders of linear regression models.

45-52

Building an Internet-Based Learning Environment in Higher Education: Learner Informing Systems and the Life Cycle Approach

Zeynep Onay
Middle East Technical University, Turkey

The last years of the millenium have witnessed an exponential growth in courses, degree and certificate programs offered on the Internet. Many universities have felt the pressure and responded to the challenge of new technologies. Middle East Technical University (METU) is the first university in Turkey to initiate Internet-based learning through its METU-Online project. METU has taken a centralized approach for the establishment of METU-Online in order to avoid duplication of effort and enable the consolidation of scarce resources; all activities pertaining to Internet-based learning are coordinated by the Informatics Institute. This paper uses the Informing Science Framework to present the institutional system established at METU, and describes the activities involved in implementing METU-Online in relation to the phases of the systems development life cycle.  It then introduces the main features of METU-Online and provides an appraisal of its impact. The Informing Science Framework defines the components of Internet-based learning. The life cycle approach shows the phases involved in building learner informing systems and the activities that need to be carried out at each phase. The Informing Science Framework and the life cycle approach together constitute a template that may be used by other universities embarking on such a mission.