Dr. Phil-Adrian Klotz
Dr. Phil-Adrian Klotz
Postdoc at Düsseldorf Institute for Competition Economics (DICE)
Postdoc at Düsseldorf Institute for Competition Economics (DICE)
Embedded Files
I am a post-doctoral researcher at the Düsseldorf Institute for Competition Economics (Heinrich Heine University) . I hold a Ph.D. from the University of Giessen, where I completed my dissertation "Five Empirical Essays on Competition Policy and Health Economics".
My research sits at the intersection of Applied Microeconomics and Empirical Industrial Organization. I study price regulation in international book markets and competition restrictions in energy and transport markets, drawing on causal inference methods to answer these questions. More recently, I have extended this work to Causal Machine Learning.
Alongside my research, I gained experience as a scientific policy advisor and in consulting on cartel damage claims during my doctoral studies.
Contact Details
University e-mail: klotz@dice.hhu.de
Private e-mail: p.klotz@outlook.de
Postal Address: Heinrich Heine University, Oeconomicum, Building No. 24.31, Universitätsstr. 1, D-40225 Düsseldorf
News:
The paper Automatic debiased machine learning and sensitivity analysis for sample selection models (with Jakob Bjelac, Victor Chernozhukov, Jannis Kueck, and Theresa M. A. Schmitz) is now published in Proceedings of Machine Learning Research:
Abstract
In this paper, we extend the Riesz representation framework to causal inference under sample selection, where both treatment assignment and outcome observability are non-random. Formulating the problem in terms of a Riesz representer enables stable estimation and a transparent decomposition of omitted variable bias into three interpretable components: a data-identified scale factor, outcome confounding strength, and selection confounding strength. For estimation, we employ the ForestRiesz estimator, which accounts for selective outcome observability while avoiding the instability associated with direct propensity score inversion. We assess finite-sample performance through a simulation study and show that conventional double machine learning approaches can be highly sensitive to tuning parameters due to their reliance on inverse probability weighting, whereas the ForestRiesz estimator delivers more stable performance by leveraging automatic debiased machine learning. In an empirical application to the gender wage gap in the U. S., we find that our ForestRiesz approach yields larger treatment effect estimates than a standard double machine learning approach, suggesting that ignoring sample selection leads to an underestimation of the gender wage gap. Sensitivity analysis indicates that implausibly strong unobserved confounding would be required to overturn our results. Overall, our approach provides a unified, robust, and computationally attractive framework for causal inference under sample selection.
Awards: Best Paper Award at 5th Conference on Causal Learning and Reasoning (CLEAR 2026)
___________________________________________
A recent working paper on the competitive effects of strategic duplication of infrastructure to deter market entry in the German fiber-optic broadband industry is now available here:
The impact of infrastructure duplication on investment in network industries (with Gordon Klein and Johannes Paha)
Abstract
This study provides an empirical assessment of whether competition stimulates infrastructure investment within network industries – an issue that remains unresolved through theoretical approaches alone. We examine this question in the context of fiber-optic broadband deployment by internet service providers in Germany, a sector that has drawn regulatory scrutiny amid concerns that incumbent firms engage in strategic duplication of infrastructure to deter market entry. To this end, we construct a novel dataset by applying text mining techniques to systematically extract information on fiber infrastructure duplication from newspaper reports. Employing econometric methods, we estimate the causal impact of competition on investment behavior. Contrary to the expectation that competition may spur infrastructure expansion, our findings indicate that competitive pressure is associated with a deceleration in fiber network rollout.
___________________________________________
Our working paper on the effect of the Deutschlandticket on extra-urban passenger traffic in Germany is now available on SSRN:
Derailing the Car? The Effect of Germany’s Deutschlandticket on Road Traffic (with Theresa Daniel and Maximilian Maurice Gail)
Abstract
This paper examines the causal impact of Germany’s Deutschlandticket, a flat rate nationwide ticket introduced in May 2023, on extra-urban passenger traffic. Using a synthetic difference-in-differences (DiD) approach, we construct a counterfactual for German traffic volumes utilizing automatic counting station data from Austria, Switzerland, Finland, and Great Britain. Contrary to the policy's objectives, we find that this drastic fare reduction failed to induce a lasting modal shift away from private cars. While a temporal analysis reveals a transient traffic reduction during the initial summer months of the policy (approximately 7.5%), this substitution effect vanishes rapidly and does not persist into the subsequent year. These findings are robust to the spatial composition of the donor pool, as well as to road-type and day-of-week heterogeneity. Our results are consistent with recent literature suggesting that standalone demand-side subsidies are insufficient to overcome non-monetary generalized costs, such as the reliability issues and capacity constraints currently affecting the German rail network. Consequently, the efficacy and efficiency of the Deutschlandticket as a climate policy instrument remains highly questionable.
Media Coverage: Neue Ruhr Zeitung (NRZ)
Page updated
Google Sites
Report abuse