Professor Scott Sisson
ACEMS Deputy Director, Chief Investigator
Scott is Professor and Head of Statistics in the School of Mathematics and Statistics at UNSW. He is internationally recognised for his work in computational and Bayesian statistics, and in particular for developing inferential techniques for computationally intractable models and challenging data. Scott is a recent President of the Statistical Society of Australia and member of the Australian National Committee for Mathematical Sciences. He is currently Chair of the Australiasian Chapter of the International Society of Bayesian Analysis (ISBA) and an ARC Future Fellow. Scott is a previous winner of the Moran Medal (Australian Academy of Science), the G. N. Alexander Medal (Engineers Australia) and the J. G. Russell Award (Australian Academy of Science), and is a previous Australian Research Council Queen Elizabeth II Research Fellow.
Research Interests:
Applied statistics
Bayesian inference
Big Data
Computational statistics
Computationally intractable models
Extreme vaule theory
Monte Carlo Methods
Symbolic data analysis
Qualifications:
Ph.D. in Statistics, Bristol University, U.K.
M.Sc. in Environmental Statistics and Systems, Lancaster University, U.K.
B.Sc. in Mathematics and Statistics, Lancaster University, U.K.
Projects
Publications
Books
(2018). Handbook of Approximate Bayesian Computation.
(Sisson, S., Fan Y., & Beaumont M. A., Ed.). doi: 10.1201/9781315117195
Book Chapters
(2018). Overview of ABC.
Handbook of Approximate Bayesian Computation. 3-54.
(2018). Inferences on the Acquisition of Multi-Drug Resistance in Mycobacterium Tuberculosis Using Molecular Epidemiological Data.
Handbook of Approximate Bayesian Computation. 481-511.
(2018). High-Dimensional ABC.
Handbook of Approximate Bayesian Computation. 211-242. doi: 10.1201/9781315117195-8
(2018). ABC Samplers.
Handbook of Approximate Bayesian Computation. 87-124.
(2016). Modelling extremes using approximate Bayesian computation.
(Dey, D., & Yan J., Ed.).Extreme Value Modelling and Risk Analysis. 281-306.
Invited talks, refereed proceedings and other conference outputs
(2020). Propagating uncertainty through to model forecasts: deterministic Lotka-Volterra systems as a case study.
Quantitative Ecology Virtual Meeting 2020.
(2019). Maximising the benefit of ecological data using Bayesian inference for ODEs.
Satellite Workshop Applied^2 Probability - “Uncertainty Quantification Applications”.
(2019). Scalable deep generative relational model with high-order node dependence.
33rd Conference on Neural Information Processing Systems (NeurIPS 2019).
(2019). The past, present and future of Monte Carlo Methods.
The 12th International Conference on Monte Carlo Methods and Applications.
(2019). Variance reduction properties of the reparameterisation trick.
(Chaudhuri, K., & Sugiyama M., Ed.).The 22nd International Conference on Artificial Intelligence and Statistics. 89, 2711-2720.
(2019). Efficient Bayesian synthetic likelihood with whitening transformations.
Bayes on the Beach 2019.
(2019). Binary Space Partitioning Forest.
(Chaudhuri, K., & Sugiyama M., Ed.).The 22nd International Conference on Artificial Intelligence and Statistics (AISTATS) 2019. 89, 3022-3031.
(2019). New models for symbolic data analysis.
62nd ISI World Statistics Congress.
(2018). Rectangular Bounding Process.
ACEMS workshop on Advanced Monte Carlo methods.
(2018). Inference for extremal-$t$ and skew-$t$ max-stable models in high dimensions.
CMStatistics.
(2018). Rectangular bounding process.
32nd Conference on Neural Information Processing Systems (NIPS).
(2018). Using aggregated data to answer high-dimensional problems.
(2018). Logistic Regression Models for Histogram-valued Symbolic Data.
UNSW Mathematics and Statistics Postgraduate Conference.
(2018). The Binary Space Partitioning-Tree Process.
The 21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018). 84, 1857-1867.
(2017). Invited Presentation, Banff Canada.
BIRS Workshop, Banff, Canada, Feb 2017.
(2017). A composite likelihood based approach for max-stable processes using histogram-valued variables.
Extreme Value Analysis 2017.
(2017). Bayes on the Beach Keynote.
Bayes on the Beach.
(2017). Stochastic Patching Process.
Bayes on the Beach 2017.
(2017). Bayes On the Beach 2017.
Bayes on the Beach 2017.
(2017). New methods for symbolic data analysis (conference presentation).
SDA17 international conference, Ljubljana, Slovenia.
(2017). The binary space partitioning tree process.
ACEMS Annual Retreat poster presentation.
(2016). New models for symbolic data.
Australian Statistical Conference.
(2016). Symbolic data analysis for extremes.
International Workshop on Extremes and Rare Events.
(2016). Symbolic data analysis for extremes.
International Workshop on Computational Challenges for Multivariate Extremes.
Journal Articles
(2021). Estimation and uncertainty quantification for extreme quantile regions.
Extremes. 24, 349-375. doi: 10.1007/s10687-019-00364-0
(2020). Hidden Group Time Profiles: Heterogeneous Drawdown Behaviours in Retirement.
arXiv. arXiv:2009.01505v1,
(2020). Informing management decisions for ecological networks, using dynamic models calibrated to noisy time‐series data.
Ecology Letters. 23(4), 607-619. doi: 10.1111/ele.13465
(2020). Constructing likelihood functions for interval‐valued random variables.
Scandinavian Journal of Statistics. 47(1), 1-35. doi: 10.1111/sjos.12395
(2020). Bayesian Nonnegative Matrix Factorization With Dirichlet Process Mixtures.
IEEE Transactions on Signal Processing. 68, 3860 - 3870. doi: 10.1109/TSP.2020.3003120
(2020). Efficient data augmentation for multivariate probit models with panel data: An application to general practitioner decision-making about contraceptives.
Journal of Royal Statistical Society. 69(2), 277-300. doi: 10.1111/rssc.12393
(2020). Tools for enhancing the application of self-organizing maps in water resources research and engineering.
Advances in Water Resources - Special issue on Machine Learning. 143, 103676. doi: 10.1016/j.advwatres.2020.103676
(2019). Acceleration of expensive computations in Bayesian statistics using vector operations.
arXiv.
(2019). Efficient data augmentation for multivariate probit models with panel data: An application to general practitioner decision-making about contraceptives.
arXiv. arXiv:1806.07274v2.
(2019). Efficient Bayesian synthetic likelihood with whitening transformations.
arXiv. arXiv:1909.04857v1.
(2019). Image Denoising Based on Nonlocal Bayesian Singular Value Thresholding and Stein’s Unbiased Risk Estimator.
IEEE Transactions on Image Processing. 28(10), 4899 - 4911. doi: 10.1109/TIP.2019.2912292
(2019). Extremal properties of the univariate extended skew-normal distribution, Part A.
Statistics & Probability Letters. 147, 73 - 82. doi: 10.1016/j.spl.2018.09.018
(2019). Ensemble optimisation, multiple constraints and overconfidence: a case study with future Australian precipitation change.
Climate Dynamics. 53(3-4), 1581-1596. doi: 10.1007/s00382-019-04690-8
(2019). Extremal properties of the multivariate extended skew-normal distribution, Part B.
Statistics & Probability Letters. 147, 105 - 114. doi: 10.1016/j.spl.2018.11.031
(2019). Tail density estimation for exploratory data analysis using kernel methods.
Journal of Nonparametric Statistics. 31(1), 144-174. doi: 10.1080/10485252.2018.1537442
(2019). Evaluating the extent of North Atlantic Deep Water and the mean Atlantic δ^{13}C from statistical reconstructions.
Paleoceanography and Paleoclimatology. 34(6), 1022-1036. doi: 10.1029/2019PA003589
(2018). Patterns and comparisons of human-induced changes in river flood impacts in cities.
Hydrology and Earth System Sciences. 22(3), 1793-1810. doi: 10.5194/hess-22-1793-2018
(2018). Likelihood-free inference in high dimensions with synthetic likelihood.
Computational Statistics & Data Analysis. 128, 271 - 291. doi: 10.1016/j.csda.2018.07.008
(2018). The sensitivity of daily temperature variability and extremes to dataset choice.
Journal of Climate. 31(4), 1337-1359. doi: 10.1175/JCLI-D-17-0243.1
(2018). Variational Bayes with synthetic likelihood.
Statistics and Computing. 28(4), 971-988. doi: 10.1007/s11222-017-9773-3
(2018). Recalibration: A post-processing method for approximate Bayesian computation.
Computational Statistics & Data Analysis. 126, 53 - 66. doi: 10.1016/j.csda.2018.04.004
(2017). Virus removal by ultrafiltration: Understanding long-term performance change by application of Bayesian analysis..
Water Research. 122, doi: 10.1016/j.watres.2017.05.057
(2017). Bayesian belief network modelling of chlorine disinfection for human pathogenic viruses in municipal wastewater..
Water Research. 109, doi: 10.1016/j.watres.2016.11.008
(2017). Nonlinear manifold representation in natural systems: the SOMersault..
Environmental Modelling and Software. 89, doi: 10.1016/j.envsoft.2016.11.028
(2017). Models for extremal dependence derived from skew-symmetric families..
Scandinavian Journal of Statistics. 44, doi: 10.1111/sjos.12240
(2017). Extending approximate Bayesian computation methods to high dimensions via a Gaussian copula model.
Computational Statistics & Data Analysis. 106, 77-89. doi: 10.1016/j.csda.2016.07.005
(2016). Functional regression approximate Bayesian computation for Gaussian process density estimation.
Computational Statistics and Data Analysis. 103, 229-241. doi: 10.1016/j.csda.2016.05.009
(2016). Does Amazonian deforestation cause global effects; can we be sure?.
Journal of Geophysical Research: Atmospheres. 121(10), 5567-5584. doi: 10.1002/2015JD024357
(2016). A dimension range representation (DRR) measure for self-organizing maps.
Pattern Recognition. 53, 276-286. doi: 10.1016/j.patcog.2015.11.002
(2016). Adaptive optimal scaling of Metropolis-Hastings algorithms using the Robbins-Monro process.
Communications in Statistics - Theory and Methods. 45(17), 5098-5111. doi: 10.1080/03610926.2014.936562
(2015). Exploring the relationship between Aboriginal population indices and fire in Australia over the last 20,000years.
Palaeogeography, Palaeoclimatology, Palaeoecology. 432, 49-57. doi: 10.1016/j.palaeo.2015.04.030
(2015). Bayesian threshold selection for extremal models using measures of surprise.
Computational Statistics & Data Analysis. 85, 84-99. doi: 10.1016/j.csda.2014.12.004
(2015). Modelling pathogen log10 reduction values achieved by activated sludge treatment using naïve and semi naïve Bayes network models.
Water Research. 85, 304-315. doi: 10.1016/j.watres.2015.08.035
(2015). Developing state and transition models of floodplain vegetation dynamics as a tool for conservation decision-making: a case study of the Macquarie Marshes Ramsar wetland.
Journal of Applied Ecology. 52(3), 654-664. doi: 10.1111/1365-2664.12410
(2015). Increasing dependence on foreign water resources? An assessment of trends in global virtual water flows using a self-organizing time map.
Ecological Informatics. 26, 192-202. doi: 10.1016/j.ecoinf.2014.05.012
Publicly available softwares
Technical reports and unrefereed outputs
(2019). A longitudinal analysis of the developmental trajectories of domain specific and domain generic abilities in high-level football players.
(2018). Efficient data augmentation for multivariate probit models with panel data: An application to general practitioner decision-making about contraceptives.
