Speakers

Home | Committees | Sponsors | Speakers | Important dates | Registration | Scientific Programme | Instructions for Speakers | Travel and Accommodation | Nordplus Support | Contacts |

Speakers

Tomasz Żądło (University of Economics in Katowice)

Fundamentals and Recent Developments in Small Area Estimation

Tomasz Żądło is employed as an associate professor at the Department of Statistics, Econometrics and Mathematics at the University of Economics in Katowice. His research interests focus on small-area estimation, mixed models and bootstrap methods. He is a co-author of the R package “qape”, available on CRAN, designed for prediction, accuracy estimation and Monte Carlo analysis under linear mixed models. He has published numerous papers in international journals, including International Journal of Machine Learning and Cybernetics, The R Journal, Social Indicators Research, Journal of Official Statistics, Australian and New Zealand Journal of Statistics and Statistical Papers. He is an elected member of the International Statistical Institute, a country representative of the International Association of Survey Statisticians, and a member of the Scientific Statistical Council, an advisory and opinion-making body for statistical research methodology supporting the President of Statistics Poland. 

Anastasija Tetereva (Erasmus University Rotterdam)

Tree-Based Methods for Survey Data and Beyond: Modeling Structured Heterogeneity with Interpretable ML

Anastasija Tetereva is an Assistant Professor at the Erasmus School of Economics, Erasmus University Rotterdam. Her research lies at the intersection of financial econometrics, asset pricing, and machine learning, with a focus on developing data-driven methods for forecasting, portfolio allocation, and risk measurement. She designs econometric and machine-learning frameworks that exploit rich financial information - such as high-dimensional firm characteristics, macro-financial variables, textual disclosures, and other unstructured data - to improve prediction and economic decision-making. Her work includes tree-based and ensemble approaches for volatility and tail-risk forecasting, machine-learning methods for asset allocation and stochastic discount factor construction. Her research emphasizes interpretable, economically grounded machine-learning tools that deliver measurable improvements.

Marco Puts (Statistics Netherlands)

Marco Puts is a methodologist at Statistics Netherlands. His work focuses on the methodological foundations of using Machine Learning in official statistics. He has contributed important ideas to survey methodology, including work related to the Total Machine Learning Error Framework, which extends classical survey error thinking to AI-based statistical production. Marco’s research aims to support the responsible and transparent use of machine learning in modern statistical systems.

Danutė Krapavickaitė (Vilnius Gediminas Technical University)

Danutė Krapavickaitė worked as a professor at the Vilnius Gediminas Technical University and authored several textbooks in Lithuanian. Currently she is a data analyst and researcher at the department of Mathematical Statistics, specializing in the survey methodology and official statistics. Her work focuses on sampling design, survey estimation, and the application of statistical methods in socio‑economic data analysis. Danutė has extensive experience in the field, having worked at Statistics Lithuania for almost twenty years, where she played a key role in the development of the social surveys. Danutė Krapavickaitė is a member of IASS, she has been a long term editor of the IASS newsletter The Survey Statistician and editor of Lithuanian Journal of Statistics. She is one of the creators of the BNU Network on Survey Statistics.

Kaja Sõstra

Developing transparent and harmonised publication thresholds for EU-LFS data dissemination

Contributed papers

TBA