Cloud created by:
16 September 2014
The October eLC event focuses on retention, and what can be done to improve it.
Date: Tuesday 14th October 2014
Time: 10:00 to 12:30
Location: Library Seminar Rooms 1 and 2.
- 10:00 – 10:30 Using predictive modeling to identify at risk students - Zdenek Zdrahal (KMI)
- 10:30 – 11.00 The MCT Faculty’s level 1 retention review - Christine Pearson, Derek Jones, Karen Kear & Sally Crighton (MCT)
- 11:00 – 11:15 Coffee break
- 11:15 – 11:45 Completion rates – a false trail to measuring course quality? - Alastair Creelman (Linnaeus University, Sweden)
- 11:45 – 12:15 Evaluating and sharing evidence of retention interventions - Simon Cross (IET)
- 12.15 – 12.30 Overview and discussion
- 12.30 Close
This event has been recorded and can be viewed via Stadium except for the recording of 'Completion rates - a false trail to measuring course quality?'.
Using predictive modeling to identify at risk students
Zdenek Zdrahal (KMi)
The OU Analyse project aims to use machine learning methods to identify students who are at risk of failing a module. Based on the VLE and demographic data recorded in previous presentations, we built four predictive models. For two selected 2014B level 1 modules we sent to the Student Support teams weekly predictions of at-risk students. The OU Analyse dashboard with the module and individual student views has been designed and implemented. The dashboard will be demonstrated.
The MCT Faculty’s level 1 retention review
Christine Pearson, Derek Jones, Karen Kear & Sally Crighton (MCT)
The Maths, Computing and Technology faculty recently carried out a review of retention on its key level 1 modules. This project aimed to investigate factors affecting retention at level 1 and actions that could improve retention. Members of the project team will present an overview of the methods used to investigate level 1 retention, and the main findings and planned actions.
Completion rates – a false trail to measuring course quality?
Alastair Creelman (Linnaeus University, Sweden)
Statistics are often used to reveal significant differences between online and campus-based education. The existence of online courses with low completion rates is often used to justify the inherent inferiority of online education compared to traditional classroom teaching. Our study revealed that this type of conclusion has little substance. We have performed three closely linked analyses of empirical data from Linnaeus University aimed at reaching a better understanding of completion rates. Differences in completion rates revealed themselves to be more substantial between faculties than between distribution forms. The key-factor lies in design.
Evaluating and sharing evidence of retention interventions
Simon Cross (IET)
There remain many challenges associated with capturing, evaluating, claiming and sharing evidences of successful retention intervention based on learning analytics. This presentation will outline two new IET projects focused on just such questions. The first is the Intervention and Evaluation Project (part of the OU SEP). This will involve 15 large level 1 modules from across the university. The second is the European Union funded LACE (Learning Analytics Community Exchange) project. This seeks to build an international Evidence Hub to share experiences of learning analytics implementations.