Analysis of classification problems using machine learning and statistical methodologies in routine data
Category: Routine data
Recording – The introduction to the NIH statistics group and machine learning terminology
Recording – Morning presentations from Marcos del Pozo Banos, Daniel Stamate, Nazrul Islam
The field of statistical research is evolving. Large data resources are becoming more readily
available. The field is therefore adapting by introducing more effective methodologies to
facilitate analysis and/or data handling of these large data resources. This routine data event
aims to explore the functionality of machine learning techniques in handling large/routinely
collected datasets, and compare its utility against statistical techniques.
The event is open to all and will be of particular relevance to statisticians and researchers
working with large (routinely collected) data.
Speakers:
• Marcos Del Pozo Banos – Responsible use of machine learning with
routine data
• Daniel Stamate – Predicting risk of dementia with machine learning
and statistical learning: results on the CPRD and ELSA cohorts
• Nazrul Islam – Analysis of classification problems using machine
learning and traditional statistical techniques: a prequel