This web page lists material related to statistical data analysis, including lectures that I have given.

General Topics

• sPlots: This is a re-weighting technique used in particle physics, especially when validating multidimensional fit models. An example ROOT macro can be downloaded from here, along with this brief overview of what sPlots are and how to use them.

Machine Learning Topics

• Generalisation: This is the issue of trying to determine a robust MVA training that can be applied to an unseen data sample and be expected to perform well; as opposed to being fine tuned (over trained/over fitted) on statistical fluctuations within the training sample itself. provides a brief introduction to the issue and discusses decay-weight regularisation for neural networks as well as cross validation algorithms.
• Support Vector Machines: provides a brief introduction to the soft and hard margin SVM algorithms and exemplifies their application using the example of a checker board in TMVA.

Lectures

• BaBar Analysis School Lectures on Multivariate Methods BAS 2009
• Tutorials at the UK HEP Young Experimentalists and Thoerists institute on Statistical Methods YETI '07

Seminars and talks

• Support Vector Machines and generalisation in HEP Seminar at RAL (2015)
• Support Vector Machines and generalisation in HEP Contribution to ACAT (2016) (work done with Stevenson, Bethani and Hays)

Back to my home-page