ESTIMATING A PREDICTION MODEL FOR THE EARLY IDENTIFICATION OF LOW EMPLOYABILITY GRADUATES IN MALAYSIA.

This paper describes the development of a prediction model for the early identification of low employability graduates in Malaysia. A total of five proportional hazard models are estimated and using the criteria of percentage correctly and wrongly predicted, a prediction model is selected based on the percentage correctly predicted. The percentile of the predicted hazard rate is used as the employability index (EI). In the context of Malaysia, it is recommended that the 5th percentile graduates be considered as low employability graduates. With this early identification tool, specific intervention programs can be tailored for the right target groups. [ABSTRACT FROM AUTHOR]