Research

Main research interests

  • general - artificial intelligence, large language models, computational statistics, machine learning, data science
  • specific - hierarchical Archimedean copulas (contruction, fitting, sampling and testing), risk management applications, prompt engineering, counterfactual inference
  • programming languages - Python, MATLAB

Book

Journal papers

  1. J. Górecki, D. Bartl, and J. Ramík. (2024). Robustness of priority deriving methods for pairwise comparison matrices against rank reversal: A probabilistic approach. Annals of Operations Research, 333:249--273, 2024.
  2. J. Górecki. Pair programming with ChatGPT for sampling and estimation of copulas. Computational Statistics, 2023.
  3. J. Górecki and M. Hofert. Composite pseudo-likelihood estimation for pair-tractable copulas such as Archimedean, Archimax and related hierarchical extensions. Journal of Statistical Computation and Simulation, 2023.
  4. J. Górecki, M. Hofert and O. Okhrin. Outer power transformations of hierarchical Archimedean copulas: Construction, sampling and estimation. Computational Statistics & Data Analysis (open access) 155(), 2021. BibTex
  5. J. Górecki, M. Hofert and M. Holeňa. Hierarchical Archimedean Copulas for MATLAB and Octave: The HACopula Toolbox. Journal of Statistical Software. pp. 1-36, 93(10), 2020. Online at GitHub. BibTex
  6. J. Górecki, M. Hofert and M. Holeňa. Kendall’s tau and agglomerative clustering for structure determination of hierarchical Archimedean copulas. Dependence Modeling, pp. 75-87, 5(1), 2017. Online at De Gruyter (Open access). BibTex
  7. J. Górecki, M. Hofert and M. Holeňa. On structure, family and parameter estimation of hierarchical Archimedean copulas. Journal of Statistical Computation and Simulation, Taylor & Francis, pp. 3261-3324, 87(17), 2017. Online at Taylor & Francis. BibTex
  8. J. Górecki, M. Hofert and M. Holeňa. An Approach to Structure Determination and Estimation of Hierarchical Archimedean Copulas and Its Application in Bayesian Classification. Journal of Intelligent Information Systems, Springer Science+Business Media New York, pp. 21-59, 46(1), 2016. Online at Springer. BibTex

Proceedings papers (selection)

  1. J. Górecki, M. Hofert and M. Holeňa. On the consistency of an estimator for hierarchical Archimedean copulas. Proceedings of the 32nd International Conference on Mathematical Methods in Economics (MME 2014), pages 239 – 234, Olomouc, Czech Republic, 2014. BibTex
  2. J. Górecki and M. Holeňa. Structure determination and estimation of hierarchical Archimedean copulas based on Kendall correlation matrix. New Frontiers in Mining Complex Patterns, Second International Workshop, NFMCP 2013, Held in Conjunction with ECML-PKDD 2013, Prague, Czech Republic, September 27, 2013, Revised Selected Papers, pages 132-147, 2014. Online at Springer. BibTex
  3. J. Górecki and M. Holeňa. An alternative approach to the structure determination of hierarchical Archimedean copulas. Proceedings of the 31st International Con- ference on Mathematical Methods in Economics (MME 2013), pages 201 – 206, Jihlava, Czech Republic, 2013. BibTex

Software

  • Hierarchical Archimedean Copulas for MATLAB and Octave: The HACopula Toolbox. Available at GitHub.
Next