Event in November
Tuesday 15 Nov. 2016 , 17:30 -19:00
Protecting confidentiality while making data available for research and policy analysis: current trends
Speaker: Dr Christine O'Keefe
Government agencies around the world are increasingly seeking to realise the value inherent in their growing data holdings, by making data available for research and policy analysis. While care is being taken to protect confidentiality in such data releases, there have been some high profile events in which access to some publicly-released data has been terminated due to re-identifications or risks of re-identification. This talk will outline the evolution of traditional approaches to balancing use and analysis of data with confidentiality protection. In particular, this talk will highlight current trends, potential issues, and emerging approaches to addressing the issues.
Event in October
Tuesday 11 Oct. 2016 , 17:30 -19:00
Britain's Misleading Benefit Sanctions Statistics
Speaker: Dr David Webster (Honorary Senior Research Fellow)
Affiliation: School of Social and Political Sciences, University of Glasgow
This presentation will explain and discuss the main misleading features of the DWP’s published benefit sanctions statistics and their presentation, drawing on the author’s successful complaint to the UK Statistics Authority in July 2015. These particularly concern understatement of the scale of sanctions, and missing information. These statistics offer a striking illustration of the way official statistics can be abused to present a politically loaded picture, without any actually false statements being made. There will also be a brief look at the problems involved in attempting to make a definitive assessment of the severity of the sanctions regime since 1996 under JSA compared with previous regimes.
Event in September
Thursday 22 September , 17:30 - 19:15
Dragon-Kings: extreme risk events, prediction and control
Speakers: Prof. Didier Sornette
Affiliation: ETH Zurich, Department of Management, Technology, and Economics
In many complex systems, large events are believed to follow power-law, scale-free probability distributions so that the extreme, catastrophic events are unpredictable. In the last decade, I have spearheaded the concept of "dragon-kings'', these outliers of large sizes and unique origins [1,2]. Our research has shown that most extreme events in fact do not belong to a scale-free distribution. Called dragon-kings, these events are outliers that possess distinct formation mechanisms. Such specific underlying mechanisms open the possibility that dragon-kings can be forecasted, allowing for suppression and control . For certain dynamical systems, it is possible to illustrate the statistical evidence and predictability of dragon-kings.
The approach can be generalised to obtain a conceptual framework to quantify, model and predict crises in out-of-equilibrium open heterogeneous dynamical systems (ie almost all systems of interest) based on a synthesis of the theory of the renormalization group in statistical physics and bifurcation theory in mathematics combined with systematic empirical data analyses. We have recently reviewed the state of the art and some recent progress on the best statistics to detect the dragon-kings in sparse data (the outlier detection problem) . The obtained insights have important implications to address the challenges facing mankind, including finance induced instabilities in worldwide economies, debt instability, cyber-risks , industrial and nuclear risks , epidemics of obesity and chronic diseases, aging and financial retirement liabilities, the energy challenges, the water problem, the soil erosion run- away, the on-going sixth largest biological extinction, extreme industrial disasters, coupled with geopolitical risks, the problem of the stability of societies that need to steer responsible management of our complex industrial systems. We propose a novel quadrant formulation of risk management along the dimensions of stressor severity and level of predictability , in which the dragon-king regime plays a prominent role.
Reference:  D. Sornette, Dragon-Kings, Black Swans and the Prediction of Crises, International Journal of Terraspace Science and Engi\ neering 2 (1), 1-18 (2009) (http://arXiv.org/abs/0907.4290) and (http://ssrn.com/abstract=1470006)  D. Sornette and G. Ouillon, Dragon-kings: mechanisms, statistical methods and empirical evidence, European Physical Journ\ al, Special Topics 205, 1-26 (2012) (special issue on power laws and dragon-kings) (http://arxiv.org/abs/1205.1002)  Hugo L.D. de S. Cavalcante, Marcos Oria, Didier Sornette, Edward Ott and Daniel J. Gauthier, "Predictability and control \ of extreme events in complex systems", Phys. Rev. Lett. 111, 198701 (2013)  Spencer Wheatley and Didier Sornette, Multiple Outlier Detection in Samples with Exponential and Pareto Tails: Redeeming \ the Inward Approach and Detecting Dragon Kings, (http://arxiv.org/abs/1507.08689 and http://ssrn.com/abstract=2645709)  Spencer Wheatley, Thomas Maillart and Didier Sornette, The Extreme Risk of Personal Data Breaches & The Erosion of Privac\ y, Eur. Phys. J. B 89 (7), 1-12 (2016)  Spencer Wheatley, Benjamin Sovacool and Didier Sornette, Of Disasters and Dragon Kings: A Statistical Analysis of Nuclear\ Power Incidents & Accidents, Risk Analysis DOI: 10.1111/risa.12587, pp. 1-17 (2016)  Tatyana Kovalenko and Didier Sornette, Risk and Resilience Management in Social-Economic Systems, IRGC Resilience In And \ For Risk Governance (RIARG) resource guide (in press 2016) (http://ssrn.com/abstract=2775264)
Event in April:
Tuesday 12 April 2016, 17:30 - 19:15
The 2013 Scottish Schools Adolescent Lifestyle and Substance Use Survey (SALSUS)
Speakers: Sandra Robb
Affiliation: Information Services NHS National Services Scotland
Abstract: The Scottish Schools Adolescent Lifestyle and Substance Use Survey (SALSUS) is the primary source of data on substance use behaviour among young people in Scotland. Following a major revamp, the 2015 publication received the Royal Statistical Society's Best Statistical Release 'runner up' award. Come along and see how the publication was redesigned, illustrated using some of the 2013 survey's key findings.
Event in February:
Tuesday 16th February 2016, 17:30 - 19:15
Using 'big data' to understand and predict ageing
Speakers: Dr. Riccardo E. Marioni & Stuart J. Ritchie
Affiliation: Centre for Cognitive Ageing and Cognitive Epidemiology, The University of Edinburgh
Abstract: Why do people age at different rates? How well can we predict a person's physical and cognitive ageing using biological data? This talk will introduce two large longitudinal datasets of older individuals (the Lothian Birth Cohorts of 1921 and 1936) in which longitudinal cognitive, lifestyle, brain imaging, genetic, and epigenetic data have been collected. After describing the datasets, we will present two key analyses based on the neuroimaging and epigenetic resources. First, Stuart Ritchie will present a model of multiple correlates of brain ageing, comparing between variables that associate with cross-sectional brain differences and those that predict longitudinal brain changes. Second, Riccardo Marioni will discuss the latest epigenetic epidemiology research findings. Epigenetics refers to chemical changes to DNA that switch genes on and off; it is an excellent source to help us understand how environmental factors influence our biology. For example, we will discuss the estimation of an individual's 'biological age' from their epigenome, and the prediction of their subsequent mortality risk. Finally, we will discuss the prediction of an individual's BMI from genetic and epigenetic data.
Event in January:
RSS Young Statisticians' Section (YSS) Event:Statistics for soccer matches prediction
Tuesday 26 January 2016 , 17:30 - 19:30
Speaker: Dr. Robert Mastrodomenico
Affiliation: Global Sports Statistics, also RSS Honorary officer for Membership
Abstract: The increased data in sports has provided statisticians with the tools to build models of sporting events. This talk will look to show how data from soccer matches can be used to create models with the ability to predict upcoming matches. Starting from a very simple approach we will show how a modified Poisson approach is able to characterise the dynamics of the beautiful game. Following from the model definition we fit it on data from England and show how the output can be used in predicting games from the English Premier League.
Rob as RSS Honorary officer for Membership, will also discuss the merits of being a member drawing on my experiences from being involved with RSS young statisticians' section (YSS) and Council.