Statistical Methods for the Analysis of High-Dimensional and Massive Data Sets


24-25 January 2019


Queensland University of Technology, Gardens Point, Brisbane, Queensland

Big data is a fast-growing field and skills in the area are some of the most in demand today.  During these two days, we will introduce big data and some of the statistical and mathematical approaches for analysing it.  The big problem is that the data is big - the size, complexity and diversity of datasets increases every day. This means we need new solutions for analysing data. The first day tutorial will equip you for working with these solutions by introducing you to selected statistical and machine learning techniques used for analysing large datasets and extracting information. The second day will present talks covering recent novel Statistical and Mathematical approaches to analyse complex large datasets.

The first day is a tutorial style day using R software suitable to analyse High-Dimensional and Massive Data sets.

Presenters and tutors include:

  • Professor Benoit Liquet, University of Pau and Pays de L’Adour (E2S), ACEMS (QUT)
  • Dr Pierre Lafaye de Micheaux  (UNSW)


Outline program

Opening Remarks: Kerrie Mengersen, Chief Investigator at ACEMS


Day 1 - Thursday, 24 January

A gentle tutorial style day with R software and libraries.


You will be introduced to:

  • Manage massive matrices with shared memory and memory-mapped files with the bigmemory R package
  • Divide and Recombine Strategy 
  • Parallel computing on a virtual machine
  • Sparse model for high dimensional data with the glmnet R package
  • Lasso and elastic-net linear and logistic models for ultrahigh-dimensional data with the  biglasso R package
  • Sparse Partial Least squares approaches for big-data with the bigsgPLS R package 

This is a hands on workshop. Attendees should have had some experience working with the R language before and should bring along a machine (Windows, Mac, Linux all great) running a recent build of R.


Day 2 - Friday, 25 January

A series of talks linking to Day 1 activities.  The participants include:

  • Professor Rob Hyndman (Monash)
  • Professor Robert Kohn (UNSW)
  • Professor Matt Wand (UTS)
  • Professor Matt Roughan (The University of Adelaide)
  • Dr Tamara Broderick (MIT) 
  • Dr Antonietta Mira (USI)
  • Dr Francesco Bartolucci (Perugia University)
  • Leah South (QUT)
  • Dr Pierre Lafaye de Micheaux (UNSW)
  • Dr Alan Huang (UQ)