Research interests

My research focuses on:

  • Penalized likelihood theory and methods
  • Statistical computing and algorithms for complex regression models
  • Methods for clustering

I also engage in cross-disciplinary work, focusing on data-analytic settings in sports science (uncovering the links between human behaviour, health, fitness and overall wellbeing), finance (modelling the dynamics of financial indicators with structural dependencies), and earthquake engineering (assessment of the vulnerability of the built environment from post-hazard survey data).

Research groups and themes

The research groups and themes that I participate are:

Publications

  • Kosmidis I and Karlis D (2016). Model-based clustering using copulas with applications. Statistics and Computing, 26, 1079–1099. [DOI] [arXiv] Methods Applications
  • Maqsood T, Edwards M, Ioannou I, Kosmidis I, Rossetto T and Corby N (2016). Seismic vulnerability functions for Australian buildings by using GEM empirical vulnerability assessment guidelines. Natural Hazards, 80, 1625-1650. [DOI] Applications
  • Panayi E, Peters GW and Kosmidis I (2015). Liquidity commonality does not imply liquidity resilience commonality: A functional characterisation for ultra-high frequency cross-sectional LOB data. Quantitative Finance, 15, 1737-1758. [DOI] [arXiv] Applications
  • Ames M, Peters GW, Bagnarosa G and Kosmidis I (2015). Upside and downside risk exposures of currency carry trades via tail dependence. In: Glau, M. Scherer, and R. Zagst (Eds.), Innovations in Quantitative Risk Management Volume 99 of Springer Proceedings in Mathematics Statistics 163-181. [DOI] [arXiv] Applications Methods
  • Kosmidis I (2014). Bias in parametric estimation: reduction and useful side-effects. WIRE Computational Statistics, 6, 185-196. [DOI] [arXiv] Methods
  • Kosmidis I (2014). Improved estimation in cumulative link models. Journal of the Royal Statistical Society: Series B, 76, 169-196. [DOI] [arXiv] Theory Methods
  • Grün B, Kosmidis I and Zeileis A (2012). Extended Beta regression in R: Shaken, stirred, mixed, and partitioned. Journal of Statistical Software, 48, [DOI] Software Methods
  • Kosmidis I and Firth D (2011). Multinomial logit bias reduction via the Poisson log-linear model. Biometrika, 98, 755-759. [DOI] Theory Methods
  • Latuszynski K, Kosmidis I, Papaspiliopoulos O and Roberts GO (2011). Simulating events of unknown probabilities via reverse time martingales. Random Structures and Algorithms, 38, 441-452. [DOI] Methods
  • Kosmidis I and Firth D (2010). A generic algorithm for reducing bias in parametric estimation. Electronic Journal of Statistics, 4, 1097-1112. [DOI] [R Code and an example zip] Methods Theory
  • Kosmidis I and Firth D (2009). Bias reduction in exponential family nonlinear models Biometrika, 96, 793-804. [DOI] Theory
  • Kosmidis I (2008). The profileModel R package: Profiling objectives for models with linear predictors. R News, R Foundation for Statistical Computing, 8/2, 12-18. [DOI] Software Methods

Preprints packman

  • Frick H and Kosmidis I (2016). trackeR: Infrastructure for running and cycling data from GPS-enabled tracking devices in R. [trackeR package vignette] Software
  • Kosmidis I, Guolo A and Varin C (2016). Improving the accuracy of likelihood-based inference in meta-analysis and meta-regression. [arXiv] Theory Methods Applications
  • Kosmidis I and Passfield L (2015). Linking the performance of endurance runners to training and physiological effects via multi-resolution elastic net. [arXiv] Applications
  • Kosmidis I and Karlis D (2010). Supervised sampling for clustering large data sets. [CRiSM working paper] Methods Applications
  • Kosmidis I (2010). On iterative adjustment of responses for the reduction of bias in binary regression models. [CRiSM working paper] Methods Applications

PhD thesis

Selected presentations