Jonathan Gendron, Ph.D.
Quantitative methodology expert helping researchers choose the right methods to get the right inferences!
Jonathan Gendron, Ph.D.
Quantitative methodology expert helping researchers choose the right methods to get the right inferences!
Email: jegendron@vt.edu LinkedIn: Link
Research Interests: Applied Quantitative Methods (Econometrics/Statistics/Business Analytics), Simulation-Based Inference, Model Evaluation, Validation, and Selection, Forecasting and Time Series Methods, Machine Learning Applications, Meta-Regression Methodology
Research Highlights: One published manuscript, and job market paper (under review) presented at
Camp Econometrics XIX
2025 International Association of Applied Econometrics
2025 DC-MD-VA Econometrics Workshop
2025 Southern Economics Association
Teaching Highlights:
Taught 7 sections across 4 undergraduate ECON courses (including intermediate)
Evaluations consistently above department and college averages
2025 Flash Talk on Job Market Paper
2019 Flash Talk on Master's Thesis
Currently Researching:
Automated Diagnostics for Meta-Regressions: A Machine Learning Framework
Efficacy of Location-level Fixed Effects in Experimental Economics: A Simulation Study on Heterogeneity in Location
Permutation Tests Improve Upon Model-Free Dependence Measures
Cost Saving with Misspecification Testing - Assuring Optimal Experimental Design
From Normality to Reality: Improving Experimental Economic Analysis with Distributions
Job Market Paper:
(Paper Link, Github Link, Flash Talk Link)
Conferences: Has been presented at
Camp Econometrics XIX
2025 International Association of Applied Econometrics
2025 DC-MD-VA Econometrics Workshop
(upcoming) 2025 Southern Economics Association
Contributions: The following are new to the literature
Provide a practitioner's guide to model selection
Test the performance of relevant methods with various degrees of location and time heterogeneity
Test the efficacy of two new methods in the experimental economics and meta-analysis simulation literature
Abstract: In this paper, we conduct a simulation study with subject-level data to evaluate conventional meta-regression approaches (study-level random, fixed, and mixed effects) against seven methodology specifications new to meta-regressions that control joint heterogeneity in location and time (including a new one that we introduce). We systematically vary heterogeneity levels to assess statistical power, estimator bias and model robustness for each methodology specification. This assessment focuses on three aspects: performance under joint heterogeneity in location and time, the effectiveness of our proposed settings incorporating location fixed effects and study-level fixed effects with a time trend, as well as guidelines for model selection. The results show that jointly modeling heterogeneity when heterogeneity is in both dimensions improves performance compared to modeling only one type of heterogeneity.