About
I am an econometrician specialising in panel data methods, factor models, and machine learning for causal inference. My current research develops estimators and software tools that uncover latent group structures and interactive fixed effects in large panel datasets.
I am a Senior Research Officer in ISER (Institute for Social and Economic Research) at University of Essex. I completed PhD in Economics at the University of Birmingham (2020–2025), supervised by Marco Barassi and Yiannis Karavias.
Research
Job Market Paper
Double Machine Learning with High-dimensional Interactive Fixed Effects[arXiv][slides][R package]
with A. Polselli and P. S. Clarke
Factor structures are central to empirical work in economics and finance, and are usually used to model time-varying unobserved heterogeneity through interactive fixed effects (IFE). Existing IFE estimators rest on low-dimensional and linear specifications in the covariates, assumptions which are increasingly restrictive in applications drawing on rich datasets with controls of unknown functional form. This paper develops a Double Machine Learning estimator for the high-dimensional partially linear panel model with interactive fixed effects (panel DML-IFE). The method combines projection-based defactorisation of the data, in the spirit of Common Correlated Effects (CCE), with a Neyman-orthogonal score function and cross-fitting procedure, and accommodates low-rank factor structures in outcomes and treatments alongside high-dimensional, potentially nonlinear covariate effects estimated by machine learning algorithms. Monte Carlo simulations show that panel DML-IFE outperforms conventional IFE estimator outside the correctly-specified linear case, with bias reduction driven primarily by the time and covariate dimensions. An empirical application to U.S. stock returns shows that several effects documented under linear specifications lose statistical significance once high-dimensional nonlinear confounding and the presence of IFE are jointly accounted for.
Working Papers
-
Panel VAR Model With Latent Group Structures
Univariate panel models with interactive fixed effects have been well discussed in previous studies. This paper studies the multivariate panel vector autoregression (PVAR) model with group-based factors. It is flexible: the number of groups, the group membership in each group, and the number of group factors in each equation are not pre-specified, and the model can be extended to group-specific heterogeneous coefficient Panel VAR. Furthermore, it is a parsimonious structural model that is easy to compute. The paper derives the asymptotic distribution and establishes consistency of the estimator for N and T tending to infinity.
-
Group Patterns in Income Inequality and Economic Growth
The relationship between income inequality and economic growth has been debated for a long time. This article uses the grouped fixed effects estimator to examine the growth-inequality nexus across countries. Results indicate a non-linear relationship consistent with the Kuznets curve — inequality has a positive impact on growth at low levels but a negative impact at high levels. The paper also reveals heterogeneity in the response of growth to inequality across groups. Results are robust to two different Gini indexes and different model specifications.
-
Critical Review of Carbon-Emitting Energy as an EKC Regressor: New Evidence from US State-Level Data
The introduction of total fossil fuel or energy consumption as a regressor variable has become increasingly common in research on the carbon Kuznets curve (EKC). Given the way CO₂ emissions are calculated, this empirical strategy implies a clear endogeneity problem. The paper proposes an alternative model applied to US state-level panel data; empirical results show that bias on the parameters of interest may be important enough to warrant avoiding this common empirical strategy.
Packages
-
xtife: Interactive Fixed Effects Estimator for Panel Data in R
An R package implementing the interactive fixed effects estimator for panel data.
-
pvarife: Interactive Fixed Effects Estimator for Panel VAR Models in R
An R package implementing the interactive fixed effects estimator for panel vector autoregressive (VAR) models.
-
xtifedml: Double Machine Learning for Panel Models with Interactive Fixed Effects
-
pgfe: Grouped Fixed Effects in Panel Data Models in R
An R package implementing the grouped fixed effects (GFE) estimator (Bonhomme & Manresa 2015) for panel data. Available on GitHub.
CV
Working Experience
Education
References
- Marco Barassi Associate Professor in Econometrics, University of Birmingham
- Yiannis Karavias Professor in Finance, Brunel University London
- Paul Clarke Professor of Social Statistics, Director of ISER, University of Essex
Contact
Email: Binzhi.Chen@essex.ac.uk
GitHub: github.com/Rickchen0910
LinkedIn: linkedin.com/in/binzhi-chen-aa03ba18a
Phone: +44 (0)7931 174273