Find Academic Supervisors

Juan Juan CaiView profile

Associate Professor

• Statistics of Extremes
• Asymptotic Statistics
• Non-Parametric Statistics
• +3 more

Dr. Juan Juan Cai serves as an Associate Professor in the Department of Econometrics and Data Science at Vrije Universiteit Amsterdam's School of Business and Economics and holds a Research Fellow position at the Tinbergen Institute. Her academic leadership spans statistical methodology development and interdisciplinary applications in high-impact domains. Education: PhD in Statistics from Tilburg University (2012), dissertation: "Estimation concerning risk under extreme value conditions" Research Focus: Dr. Cai pioneers advanced techniques in Statistics of Extremes and Asymptotic Statistics , specializing in probabilistic forecasting of rare events. Her work bridges theoretical rigor with practical solutions for financial risk modeling, epidemiological analysis (including SARS-CoV-2 viral load studies), and cancer survival prediction, employing non-parametric frameworks and quantile-based methodologies. Publication Trends: Recent output (2023-2025) reveals a strategic expansion from core extreme value theory into machine learning integration (e.g., gradient boosting for quantile regression) and cross-disciplinary health applications. Over 80% of her work addresses multivariate regular variation and extreme event modeling, with growing emphasis on causal inference frameworks for real-world data. Honors: NWO Open competition grant (2024) for "Predicting cure chances and long term survival of cancer patients" Research Leadership: As Principal Investigator for the NWO-funded "Startersbeurs" project (2023-2028), she directs a team advancing statistical methods for finance and survival analysis. Her grant portfolio combines theoretical innovation with translational health research, evidenced by media coverage and interdisciplinary citations. Professional Ecosystem: Through the Tinbergen Institute, she cultivates collaborations across Dutch economic research institutions, leveraging networks in both academia and public health sectors to drive methodological advancements in extreme event modeling.

Mario Dos Reis BarrosView profile

Professor

• Statistical Phylogenetics
• Molecular Evolution
• Bayesian Statistical Methods
• +5 more

Dr. Mario Dos Reis Barros is a Reader in Statistical Phylogenetics at Queen Mary University of London, affiliated with the School of Biological and Behavioural Sciences. His research focuses on developing statistical methods for understanding species evolution, including divergence time estimation and genomic data analysis. Education: Bachelor's in Biology from Universidad Simón Bolívar (Venezuela) MSc in Bioinformatics from Birkbeck College, London PhD in Molecular Evolution from Birkbeck College, London Research interests include Bayesian statistical methods, molecular evolution, and phylogenetic analysis. Notable contributions include the development of methodologies for integrating morphological and genomic data to reconstruct evolutionary histories. Grants and collaborations involve work with the Francis Crick Institute, University College London, and the Natural History Museum. His lab (dosReis Lab) maintains the mcmc3r R package for phylogenetic analysis. Labs/Teams: dosReis Lab (specializing in evolutionary genomics and Bayesian phylogenetics).

Melike Oguz AlperView profile

Lecturer

• Finite population sampling design and inference
• Variance estimation
• Complex survey data analysis
• +4 more

Melike Oguz Alper is a Lecturer in Social Statistics at the University of Southampton, based in the Department of Social Statistics and Demography within the Faculty of Social Sciences. She joined the university as a lecturer in 2022 after working at Statistics Norway. Her educational background includes: BSc in Mathematics from Middle East Technical University in Ankara, Turkey MSc in Social Statistics from University of Southampton (2012) PhD in Social Statistics from University of Southampton (2016) Melike's research focuses on advanced statistical methodologies for complex survey data. Her primary research interests include: Finite population sampling design and inference Variance estimation of change in complex parameters under rotating panel surveys Empirical likelihood inference when modelling complex survey data Graph sampling methodologies Her work bridges theoretical statistics with practical applications in official statistics, developing innovative approaches to handle hierarchical and complex survey data structures. Her publication record shows consistent expertise in empirical likelihood methods and complex survey design, with significant contributions to labor force survey methodology and variance estimation techniques. Many of her publications address practical challenges in official statistics, particularly related to the Norwegian Labour Force Survey. Professional experience includes: Lecturer in Social Statistics at University of Southampton (2022-present) Researcher at Statistics Norway (part-time) Assistant expert at Turkish Statistical Institute (TurkStat) Melike teaches postgraduate modules including Survey Fundamentals, Complex Survey Data Analysis, Analysis of Hierarchical Data, Data Science Foundations, and Evaluation & Monitoring. She also delivers professional training courses in Graph Sampling, Survey Sampling, and various statistical methods.

• Extreme Value Theory
• Statistical Modeling
• Multivariate Statistics
• +3 more

Anthony Christopher Davison is a Professor at the Institute of Mathematics within the School of Basic Sciences at École polytechnique fédérale de Lausanne (EPFL). He maintains an active research program in statistical methodology with a particular focus on extreme value theory and its applications across various domains including climate science, environmental statistics, and insurance. His work bridges theoretical developments with practical applications, addressing challenging problems in multivariate and spatial extremes. His research interests span Extreme Value Theory , Statistical Modeling , Multivariate Statistics , Spatial Statistics , and Bayesian Inference . Professor Davison has made significant contributions to the understanding of extremal dependence structures, developing novel methodologies for modeling multivariate extremes using structural equation models, graphical representations, and flexible nonparametric approaches. His work often addresses the challenges of non-stationarity in extreme events, particularly relevant in climate change contexts. Analysis of his recent publications reveals a consistent focus on advancing methodological frameworks for extreme value analysis while maintaining strong connections to real-world applications. His work demonstrates increasing sophistication in handling high-dimensional extremal dependence structures and addressing challenges in causal inference for extreme events. The publications span theoretical developments in statistical methodology alongside applications in climate science, environmental risk assessment, and insurance modeling. Professor Davison has supervised numerous doctoral students including Mario Krali, Timmy Rong Tian Tse, and Sonia Alouini, whose theses address cutting-edge problems in extreme value theory. His research has been supported by various funding bodies including the Swiss National Science Foundation and other Swiss foundations.

• Statistics
• Econometrics
• Robust Estimation
• +3 more

Anna Clara Monti is a Full Professor in the Department of Law, Economics, Management and Quantitative Methods (DEMM) at the University of Sannio. Her research focuses on statistical inference, asymptotic theory, robust estimation, and time series analysis. Key research areas: Statistics, Econometrics, Robust Estimation, Asymptotic Theory, Time Series Analysis Notable contributions: Methodological advancements in portmanteau tests, skew normal distribution estimation, M-estimator confidence limits, and concentration ratio bias correction Contact: acmonti@unisannio.it

Thomas S RichardsonView profile

Professor

• Graphical Models
• Causal Inference
• Bayesian Inference
• +3 more

Thomas S Richardson is a Professor at the University of Washington, holding adjunct appointments in Economics and Electrical Engineering. He is also affiliated with the eScience Steering Committee and Center for Advanced Studies in the Behavioral Sciences at Stanford University (Fellow, 2004). His research focuses on graphical models, algorithmic model selection, Bayesian inference, causal models, and their applications in economics and biostatistics. BA, University of Oxford MS and PhD, Carnegie Mellon University Key research areas include: Causal Inference: Instrumental variable models, counterfactuals, SWIGs (Single World Intervention Graphs), and identification of direct effects. Graphical Models: Acyclic directed mixed graphs, nested Markov properties, marginal log-linear parametrizations, and latent variable modeling. Applications: Epidemiology, econometrics, bone biology, and ecological inference. His recent publications emphasize causal effect bounds, finite population testing, and structural nested mean models. Articles span topics like SWIGs, IV model analysis, and high-dimensional causal discovery. Scientific Awards: Fulbright Fellowship (2014) Institute for Advanced Studies, University of Bologna (2007) Center for Advanced Studies in Behavioral Sciences, Stanford (2004) Rosenbaum Fellow, Isaac Newton Institute (1997) Rousseeuw Prize for Statistics (2022)

Brunero LiseoView profile

Professor

• Bayesian Statistics
• Copulas
• Stochastic Processes
• +10 more

Brunero Liseo is a Full Professor of Statistics at the Department of Methods and Models for Economics, Territory, and Finance (MEMOTEF), Sapienza University of Rome. He teaches Basic Statistics and Advanced Statistical Methods in Economics and Finance programs. His research focuses on: Bayesian Statistics (objective priors, hierarchical models) Copula Theory (conditional copulas, vine copulas) Stochastic Processes (skew-Brownian motion, long-memory processes) Statistical Modeling (Gaussian extensions, data integration) Recent work includes applications in financial risk analysis , population estimation , and data linkage . He is involved in the research project New Statistical Methods for the Analysis of Human Migration .

Siem Jan KoopmanView profile

Professor

• Time Series Econometrics
• Financial Econometrics
• Forecasting
• +4 more

Siem Jan Koopman is a Full Professor of Econometrics at the Department of Econometrics, School of Business and Economics, Vrije Universiteit Amsterdam. He is also a Research Fellow at the Tinbergen Institute and holds a long-term Visiting Professor position at CREATES, University of Aarhus. His academic career includes positions at the London School of Economics and CentER (Tilburg University), with long-term visits at the US Bureau of the Census, European University Institute, and European Central Bank. Dr. Koopman earned his PhD in Statistics from The London School of Economics and Political Science between 1989 and 1992, with his degree awarded on March 30, 1992. Professor Koopman's research spans several interconnected areas of econometrics, with a particular focus on time series analysis. His work centers on state space methods, score-driven time-varying parameter models (GAS models), and dynamic factor models. He has made significant contributions to the fields of financial econometrics, forecasting methodologies, and simulation-based estimation techniques. His research bridges theoretical developments with practical applications across economics, finance, and climate science, demonstrating the versatility of econometric methods in addressing complex real-world problems. Koopman's work often involves developing innovative statistical approaches to model time-varying parameters and extract meaningful signals from noisy data. His recent publications reveal a continued emphasis on advancing methodological frameworks for time series analysis, with increasing applications to climate modeling and environmental economics. There's a clear trajectory toward more sophisticated modeling of nonlinear dynamics, volatility, and interdependencies in economic and financial systems. His work increasingly bridges econometrics with climate science, particularly in analyzing CO2 emissions, climate variability, and the economic impacts of natural disasters. Journal of Applied Econometrics Distinguished Author Fellow of the Society of Financial Econometrics (SoFiE) Professor Koopman has supervised 30 PhD theses, demonstrating his significant contribution to mentoring the next generation of econometricians. His research has been supported by multiple competitive grants including the Labex Louis Bachelier grant from the Institut Europlace de Finance, research grants from the National Bank of Poland, and the VILLUM Visiting Professor Programme grant from the Velux Foundation. These grants have supported work on portfolio allocation, interest rate forecasting, and systemic risk analysis. As a Statistical Software Developer, Koopman has created and maintained important econometric tools including STAMP and SsfPack, which are widely used in academic and professional settings for time series analysis. These software packages implement state space methods and have become standard tools in the field of econometrics.

Oskar HenrikssonView profile

Research Fellow

• Algebraic Geometry
• Tropical Geometry
• Reaction Network Theory
• +2 more

Oskar Henriksson is a Research Fellow at the Department of Mathematical Sciences within the Faculty of Science at the University of Copenhagen. His office is located at Universitetsparken 5, 2100 Copenhagen. He completed his PhD in 2025 at the same institution under the supervision of Elisenda Feliu, focusing on algebraic methods in reaction network theory. Henriksson's research centers on computational algebraic geometry, tropical geometry, and combinatorial methods applied to reaction networks and algebraic statistics. He specializes in Gröbner bases, toric varieties, homotopy continuation, and tropical geometry, with applications in biological systems and statistical modeling. His recent publications focus on parametrized polynomial systems, genome reconstruction, and geometric methods in statistics. Thematic analysis shows strong emphasis on algorithmic approaches to biological and statistical problems through algebraic frameworks. His work is supported by two major grants: the ERC Consolidator Grant 'Signs, polynomials, and reaction networks' (POSALG-101044561) and the Novo Nordisk Foundation project (NNF20OC0065582).

Anindya BhadraView profile

Professor

• Bayesian methods for high-dimensional and complex data
• Computational statistics
• Applications of statistics in life sciences
• +9 more

Anindya Bhadra is a Professor in the Department of Statistics at Purdue University and a University Faculty Scholar. His research focuses on Bayesian methods for high-dimensional and complex data, computational statistics, and applications in life sciences including genomics, infectious disease epidemiology, and nutrition. Research Interests: Bayesian inference for graphical models and high-dimensional data Gaussian processes with novel covariance functions (e.g., Confluent Hypergeometric) Deep learning and statistical learning intersections Measurement error models and zero-inflated data analysis Spatiotemporal modeling for geostatistics Scientific Contributions: Developed horseshoe+ estimator for ultra-sparse signal recovery Designed confluent hypergeometric covariance functions for spatial modeling Advanced posterior inference in infinite-width neural networks with heavy-tailed weights Created evidence estimation techniques for Gaussian graphical models Scientific Awards: University Faculty Scholar, Purdue University IISA 2022 Best Poster Award (for student K. Sagar) ENAR Distinguished Student Paper Award 2022 (for student K. Sagar) Editorial Roles: Associate Editor, Journal of the American Statistical Association (2020–2023) Associate Editor, Journal of Computational and Graphical Statistics (2021–present) Associate Editor, Statistical Analysis and Data Mining (2021–present) Associate Editor, Sankhya A (2018–present) Email: bhadra@purdue.edu

Bruce William TurnbullView profile

Professor

• Statistics
• Biostatistics
• Reliability Engineering
• +4 more

Bruce William Turnbull is a Professor at Cornell University in the School of Operations Research and Industrial Engineering, affiliated with the Departments of Statistical Science and Operations Research. His career spans roles at Stanford University (visiting faculty) and the University of Oxford (lecturer), but he has been a permanent faculty member at Cornell since 1976. Education : B.A. in Mathematics, Cambridge University (1967) M.S. in Operations Research, Cornell University (1970) Ph.D. in Statistics and Applied Probability, Cornell University (1971) M.A. in Mathematics, Oxford University (1973) Research Interests : Design and analysis of experiments for system reliability (engineering and biomedical applications) Statistical methods for clinical trials (group sequential analysis, adaptive designs) Spatial point process analysis (disease clustering, environmental exposure) Survival analysis with censored data Sequential analysis and statistical quality control Longitudinal biomarker modeling Publication Trends : Focus on clinical trials, reliability engineering, and spatial statistics Key subfields: survival analysis, adaptive trial design, changepoint detection, spatial clustering Collaborative work with Chris Jennison, L.C. Clark, and others in journals like Biometrika, JASA, and Statistics in Medicine Scientific Recognition : Recipient of the Snedecor Memorial Award (1979) Fellow of the American Statistical Association and Royal Statistical Society Editorial roles in journals such as Statistics in Medicine Advising & Collaborations : Advisor to students in biostatistics and statistics (not explicitly named) Consultant to organizations including Oak Ridge National Laboratory Member of Data and Safety Monitoring Committees for NIH and VA clinical trials Labs & Teams : Affiliated with the National Institute of Statistical Sciences (Board of Directors) Contributions to Cornell’s statistical research and clinical trial monitoring

Ivor SimpsonView profile

Associate Professor

• Artificial Intelligence
• Machine Learning
• Medical Image Analysis
• +12 more

Dr. Ivor Simpson is an Associate Professor in Informatics at the University of Sussex, affiliated with the School of Engineering and Informatics and part of the AI research group. He serves as the Academic Lead for Sussex AI and convenes the MRes in Advanced Artificial Intelligence. His academic career includes prior roles as a Senior Lecturer (2022–present) and Lecturer (2020–2022) in Artificial Intelligence at the same institution. His educational background includes a DPhil in Medical Image Analysis from the University of Oxford (2008–2012) and an MEng in Computer Science from the University of Southampton (2004–2008). Prior to his academic appointments, he worked as a Senior Research Scientist and Head of Machine Learning at Anthropics Technology (2014–2019) and as a Research Associate at University College London (2012–2014). Ivor’s research lies at the intersection of machine learning and applied statistics, with a focus on probabilistic modeling for imaging and temporal data. His work emphasizes uncertainty quantification, interpretable AI, and deep generative models, applied to medical image analysis, computer vision, and ecological monitoring. He is particularly interested in inverse problems, morphometry, image registration, and multi-modal MRI analysis. His recent publications (2022–2025) reflect a strong trend toward uncertainty-aware models in medical imaging, ecoacoustics, and computer vision. Topics include compressed sensing MRI, variational autoencoders, deep ensembles, and interactive ecoacoustic dashboards. These works demonstrate interdisciplinary collaboration and methodological innovation, particularly in quantifying spatial uncertainty and building interpretable representations. MICCAI Young Scientist Award (2013) for work on probabilistic non-linear registration Dr. Simpson actively supervises students, currently serving as primary supervisor for 6 PhD candidates and secondary supervisor for several others. He has led or participated in multiple research grants from EPSRC, NERC, and Innovate UK, supporting projects in ecoacoustics, MRI modeling, and machine learning applications. His teaching includes advanced machine learning, computer vision, and the MRes in Advanced AI. He leads a research team focused on interdisciplinary AI applications and collaborates widely across academia and industry.

• Robust Statistics
• Bias Reduction Methods
• Estimation Theory
• +5 more

Nicola Lunardon is an Associate Professor of Statistics at Ca' Foscari University of Venice. He holds a PhD in Statistics from the University of Padua and has held academic positions at the University of Milan-Bicocca, University of Trieste, and others. His research focuses on robust statistics, bias reduction methods, pseudo-likelihoods, and asymptotic theory. He has contributed to advancements in estimation functions and computational statistical methodologies. Current Affiliation: Department of Environmental Sciences, Computer Science and Statistics Previous Roles: Associate Professor at University of Milan-Bicocca (2019–2023), Research Fellowships at Padua and Trieste Universities (2012–2016) Research Interests: Lunardon's work emphasizes improving inferential procedures through robust statistical techniques. He has developed methods to address bias in estimating functions, tackle incidental parameters, and enhance computational efficiency. His Bayesian non-parametric approaches have been applied to molecular systems analysis. Publications span methodological contributions in top journals like Biometrika , Journal of the Royal Statistical Society , and Biometrics . Themes include global sensitivity analysis, longitudinal data modeling, and small-sample GEE estimation. Notable Software: Co-developed the ROSE package for imbalanced learning in R

• Financial Econometrics
• Applied Econometrics
• Theoretical Econometrics
• +5 more

Yiannis Dendramis is an Associate Professor in the Department of Economics at the Athens University of Economics and Business (AUEB), within the School of Economic Sciences. He has previously held academic positions as a Marie Skłodowska-Curie European Research Fellow, Lecturer at the University of Cyprus, and Lecturer and Research Fellow at Queen Mary University of London, reflecting a strong international academic profile. His research centers on Financial Econometrics , with emphasis on applied and theoretical modeling of high-dimensional data and the integration of machine learning methods into econometric frameworks. His work spans applications in finance and macroeconomics, particularly in forecasting, risk modeling, and policy evaluation. The analysis of his recent publications reveals a consistent focus on modern econometric techniques, including penalized regression, factor models, and machine learning algorithms applied to financial and macroeconomic datasets. His research contributes to both methodological advancements and empirical insights in areas such as volatility forecasting, systemic risk, and energy policy. He has published in leading journals including Econometric Theory , Journal of Banking and Finance , International Journal of Forecasting , and Energy Policy . While no specific scientific awards are mentioned in the provided text, his publication record indicates significant scholarly impact. Dendramis advises graduate students in econometrics and economics, though specific names are not listed. His research likely involves collaborations and access to institutional data resources, but no formal grants or funding programs are explicitly mentioned. He does not appear to lead a named research lab or team based on the available content.

Martin SingullView profile

Professor

• Mathematical Statistics
• Multivariate Statistical Analysis
• Statistical Inference
• +7 more

Martin Singull is a Professor and Head of Division in Applied Mathematics at the Department of Mathematics, Faculty of Science and Engineering, Linköping University. He has held academic positions at Linköping University since 2012, progressing from Assistant Professor to full Professor in 2020, and serving in leadership roles since 2016. His research is centered on mathematical statistics, particularly statistical inference for complex, high-dimensional data with repeated measurements. His research interests include: Statistical inference for repeated measurements and growth curve models Classification and discriminant analysis Multivariate statistical analysis High-dimensional data modeling Applications in public health, cardio-oncology, and development contexts Martin Singull's recent publications focus on likelihood-based classification, Edgeworth-type expansions for distribution approximation, residual analysis in GMANOVA-MANOVA models, and the estimation of misclassification probabilities. His work often involves collaboration with Dietrich von Rosen and other researchers, applying advanced statistical techniques to both theoretical and applied problems. A strong trend in his research is the development of efficient classifiers using temporal and spatial information in longitudinal data. His scientific service includes: Director for the Research School in Interdisciplinary Mathematics (2024–) Chair of the organizing committee for IWMS 2023 and LinStat2014 Team Leader for Sida-funded bilateral programs in mathematics with universities in Africa Member of the ISP Mathematics Reference Group Board member of the Faculty of Science and Engineering Martin Singull has supervised numerous PhD students, both at Linköping University and in collaborative programs in Rwanda, Uganda, Tanzania, Mozambique, and Cambodia. His advising spans theoretical statistics and applied interdisciplinary research. He leads research collaborations aimed at strengthening mathematical capacity in low-income countries, particularly in Africa. His work is supported by funding from Sida and ISP, and he is actively involved in international academic networks such as the International Workshop on Matrices and Statistics (IWMS). He is also associated with research initiatives in computational cardio-oncology, where statistical models are used to predict cardiovascular complications in cancer survivors, and has contributed to projects on fistula prevention and health outcomes in low-resource settings.