Predicting who will drop out of nursing courses: A machine learning exercise

Introduction: The concepts of causation and prediction are different, and have different implications for practice. This distinction is applied here to studies of the problem of student attrition (although it is more widely applicable). Background: Studies of attrition from nursing courses have tended to concentrate on causation, trying, largely unsuccessfully, to elicit what causes dropout. However, the problem may more fruitfully be cast in terms of predicting who is likely to drop out. Methods: One powerful method for attempting to make predictions is rule induction. This paper reports the use of the Answer Tree package from SPSS for that purpose. Data: The main data set consisted of 3978 records on 528 nursing students, split into a training set and a test set. The source was standard university student records. Results: The method obtained 84% sensitivity, 70% specificity, and 94% accuracy on previously unseen cases. Discussion: The method requires large amounts of high quality data. When such data are available, rule induction offers a way to reduce attrition. It would be desirable to compare its results with those of predictions made by tutors using more informal conventional methods. (C) 2007 Elsevier Ltd. All rights reserved.