Prof. Dr. Michael Vogt

E-Mail: michael.vogt(at)
Telefon: +49 228 73 9264
Standort: Institute for Economics
Institute: Department of Economics
Forschungsbereich: Research Area H
Geburtsdatum: 01.Jan 2017

Academic Career


PhD, University of Mannheim

2011 - 2013

Postdoc, University of Cambridge, England, UK

2013 - 2015

Assistant Professor, University of Konstanz

Since 2015

Professor of Econometrics, University of Bonn

Research Profile

I am working in the field of mathematical statistics and theoretical econometrics. My research focuses on non- and semiparametric estimation problems. The statistical methods developed in my work can for example be applied to problems in economics, finance, genetics and climatology. In recent years, I have been working intensively on problems in a time series context where certain types of nonstationarity, in particular so-called local stationarity, come into play. In this context, the main aim is to estimate functions which may evolve over time (cp. [1], [2] and [3]). Another part of my research is concerned with longitudinal data sets that involve information on a large number of subjects. In this setting, the objects to be estimated such as density or regression functions may vary across the observed subjects. As a result, the estimation target is a potentially very high-dimensional object, in particular a whole family of functions rather than only a single fixed function. In this context, the main aim is to develop flexible estimation methods that allow for complexity reduction (cp. [4], [5] and [6]).

My research on locally stationary time series and large longitudinal data sets is still very active. These two topics are an important part of my research agenda for the near future. Among other things, I'm planning to work on multiscale methods for locally stationary time series. Apart from this, I'm very interested in nonparametric clustering and classification problems. Among other things, I am working on techniques to classify nonparametric functions in longitudinal data models and on clustering methods that allow for rigorous statistical error control.

Selected Publications

[1] Michael Vogt
Nonparametric regression for locally stationary time series
Ann. Statist. , 40: (5): 2601--2633
[2] Michael Vogt, Holger Dette
Detecting gradual changes in locally stationary processes
Ann. Statist. , 43: (2): 713--740
[3] Michael Vogt
Testing for structural change in time-varying nonparametric regression models
Econometric Theory , 31: (4): 811--859
[4] Lena Boneva, Oliver Linton, Michael Vogt
A semiparametric model for heterogeneous panel data with fixed effects
J. Econometrics , 188: (2): 327--345
[5] Lena Boneva, Oliver Linton, Michael Vogt
The effect of fragmentation in trading on market quality in the UK equity market
J. Appl. Econometrics , 31: (1): 192--213
[6] Michael Vogt, Oliver Linton
Classification of non-parametric regression functions in longitudinal data models
Journal of the Royal Statistical Society: Series B (Statistical Methodology)
Publisher: Wiley Online Library
[7] Michael Vogt, Oliver Linton
Nonparametric estimation of a periodic sequence in the presence of a smooth trend
, 101: (1): 121--140
[8] M. R. Fengler, E. Mammen, M. Vogt
Specification and structural break tests for additive models with applications to realized variance data
J. Econometrics , 188: (1): 196--218

Publication List

Download Profile