Direkt zum InhaltDirekt zur SucheDirekt zur Navigation
▼ Zielgruppen ▼

Humboldt-Universität zu Berlin - High Dimensional Nonstationary Time Series

Georg Keilbar



georg.keilbar [at] hu-berlin.de


+49 30 2093 99596


Office hours:

Dorotheenstr. 1, room 0.04

Upon agreement

Postal address:

IRTG 1792 "High Dimensional Nonstationary Time Series"
School of Business and Economics
Humboldt-Universität zu Berlin
Unter den Linden 6
10099 Berlin, Germany


09/2020 - 12/2020 Visiting researcher, University of Chicago, USA (scheduled)
10/2019 - 02/2020 Visiting researcher, Xiamen University, China
2018 - present PhD student in Statistics, Humboldt-Universität zu Berlin  
2018 M.Sc. in Economics, Humboldt-Universität zu Berlin  

Working Papers

Keilbar, G. and Wang., W. (2019). Modelling Systemic Risk using Neural Network Quantile Regression, IRTG 1792 Discussion Paper

Keilbar, G. and Zhang, Y. (2020). On Cointegration and Cryptocurrency Dynamics, IRTG 1792 Discussion Paper


Work in Progress

Testing for Neglected Nonlinearity in the Conditional Quantile using Neural Networks (with W. Wang)

A projection based approach for interactive fixed effects panel data models (with J.M. Rodriguez-Poo, A. Saberon and W. Wang)


Scientific Talks


  • Economic Applications of Quantile Regression 2.0, Nova SBE, Lissabon
  • 12th Annual SoFiE Conference, Fudan University, Shanghai
  • Stat of ML Conference, Charles University, Prague
  • First Yushan Conference, NCTU, Hsinchu, Taiwan


  • Fudan Quantitative Economics and Finance Seminar, Fudan University, Shanghai


Research Interests

  • Quantile Regression
  • Non- and Semiparametric Statistics
  • Financial Econometrics
  • Empirical Process Methods