arXiv subjects

Daniel Czarnowske

Publications and source records attributed to Daniel Czarnowske.

7 recordsLinked to original sources

arXiv2026

Inference for Fixed Effects Estimators when Panels are Unbalanced

We develop the asymptotic theory for two-way fixed effects M-estimators in unbalanced panels, within a framework where both panel dimensions grow large at proportional rates. The selection process may be deterministic, stochastic, or a combination of the two. We require neither a missing-at-random condition nor a selection equation, only a conditional mean restriction on the outcome. The uncorrected estimators are asymptotically normal but not correctly centered due to incidental parameter bias and feedback bias. The latter arises when regressors or the selection indicator respond to past outcomes. We propose debiased estimators that remove both biases without requiring knowledge of which regressors or selection components are predetermined. Simulations show that the corrections remove most of the bias and restore coverage close to nominal levels. Revisiting a study on capital inflow surges and banking crises, we find that the corrections leave qualitative conclusions unchanged but substantially shift the estimated magnitudes.

econ.EM↗

arXiv2025

(Debiased) Inference for Fixed Effects Estimators with Three-Dimensional Panel and Network Data

Inference for fixed effects estimators is often unreliable due to Nickell- and incidental parameter biases. While these issues are well understood for classical two-dimensional panels, little is known about three-dimensional panel structures (e.g., sender x receiver x time). We develop inferential theory for a broad class of linear and nonlinear fixed effects M-estimators in this setting, covering bipartite, directed, and undirected network panel data, multiple specifications of additively separable unobserved effects, and both strictly exogenous and predetermined regressors. Our analysis reveals fundamentally different asymptotic properties compared to two-dimensional panels. In particular, we find a sharp dichotomy across specifications: (i) when unobserved effects vary along a single panel dimension, estimators are asymptotically unbiased, (ii) when they vary along two panel dimensions, estimators may suffer from a severe inference problem characterized by a degenerate asymptotic distribution. We resolve the latter by deriving explicit bias formulas and proposing analytically debiased estimators with nondegenerate, correctly centered asymptotic distributions. An empirical application studies dynamic network formation in a directed panel of bilateral trade relationships.

econ.EM↗

arXiv2025

The Effects of Flipped Classrooms in Higher Education: A Causal Machine Learning Analysis

This study uses double/debiased machine learning (DML) to evaluate the impact of transitioning from lecture-based blended teaching to a flipped classroom concept. Our findings indicate effects on students' self-conception, procrastination, and enjoyment. We do not find significant positive effects on exam scores, passing rates, or knowledge retention. This can be explained by the insufficient use of the instructional approach that we can identify with uniquely detailed usage data and highlights the need for additional teaching strategies. Methodologically, we propose a powerful DML approach that acknowledges the latent structure inherent in Likert scale variables and, hence, aligns with psychometric principles.

econ.GN↗

arXiv2022

A Classifier-Lasso Approach for Estimating Production Functions with Latent Group Structures

I present a new estimation procedure for production functions with latent group structures. I consider production functions that are heterogeneous across groups but time-homogeneous within groups, and where the group membership of the firms is unknown. My estimation procedure is fully data-driven and embeds recent identification strategies from the production function literature into the classifier-Lasso. Simulation experiments demonstrate that firms are assigned to their correct latent group with probability close to one. I apply my estimation procedure to a panel of Chilean firms and find sizable differences in the estimates compared to the standard approach of classification by industry.

econ.EM↗

arXiv2022

Latent Unbalancedness in Three-Way Gravity Models

Many panel data sets used for pseudo-poisson estimation of three-way gravity models are implicitly unbalanced because uninformative observations are redundant for the estimation. We show with real data as well as simulations that this phenomenon, which we call latent unbalancedness, amplifies the inference problem recently studied by Weidner and Zylkin (2021).

econ.EM↗

arXiv2020

Fixed Effects Binary Choice Models: Estimation and Inference with Long Panels

Empirical economists are often deterred from the application of fixed effects binary choice models mainly for two reasons: the incidental parameter problem and the computational challenge even in moderately large panels. Using the example of binary choice models with individual and time fixed effects, we show how both issues can be alleviated by combining asymptotic bias corrections with computational advances. Because unbalancedness is often encountered in applied work, we investigate its consequences on the finite sample properties of various (bias corrected) estimators. In simulation experiments we find that analytical bias corrections perform particularly well, whereas split-panel jackknife estimators can be severely biased in unbalanced panels.

econ.EM↗

arXiv2020

Inference in Unbalanced Panel Data Models with Interactive Fixed Effects

We derive the asymptotic theory of Bai (2009)'s interactive fixed effects estimator for unbalanced panels in which the source of attrition is conditionally random. For inference, we propose a method of alternating projections algorithm based on straightforward scalar expressions to compute the residualized variables required for bias correction and covariance matrix estimation. Simulation experiments confirm that our asymptotic results provide reliable finite-sample approximations. We also reassess Acemoglu et al. (2019). Allowing for a more general form of unobserved heterogeneity, we confirm significant effects of democratization on economic growth.

econ.EM↗