Mark E. Schaffer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mark E. Schaffer has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Achim Ahrens
ETH Zurich Switzerland
3 shared publications Achim Ahrens
ETH Zurich
2 shared publications- Christian Hansen
University of Chicago, Chicago, IL 60637
2 shared publications - Christopher F. Baum
School of Social Work, Boston College, Chestnut Hill, Massachusetts; Department of Economics, Boston College, Chestnut Hill, Massachusetts
2 shared publications Erkal Ersoy
Heriot-Watt University
2 shared publications- Gary Kleck
College of Criminology and Criminal Justice, Florida State University, Tallahassee, FL, USA
2 shared publications
Latest Publications
- Open Access
- 25 August 2026
- Published by HoChiMinh University of Banking in Asian Journal of Applied Financial Econometrics
- Vol. 1 (2) , 24-47
Short-term predictions for country-level energy demand with top-down and bottom-up stacking
Purpose - This paper examines whether stacking (Wolpert, 1992) improves short-term forecasts of global oil consumption and electricity demand during periods of major shocks, including COVID-19, geopolitical conflicts, and trade disruptions. Given diverging trends between OECD and non-OECD economies, we evaluate forecast performance separately across these regions. Design/methodology/approach - We combine XGBoost, random forest, elastic net, multi-layer perceptron, and a unit fixed-effects model within a stacking framework using a non-negative OLS meta-learner. We implement both a top-down approach, which models aggregate demand directly, and a bottom-up approach, which models disaggregated components and aggregates predictions, to assess the value of decomposition. Findings - We find that stacking provides a robust benchmark, consistently matching or outperforming the best individual learner across most specifications. In the top-down setting, stacking generally delivers the strongest performance, particularly for global and non-OECD oil demand and global electricity demand. Bottom-up stacking improves accuracy for most oil sub-aggregates and performs comparably to the best base learner for electricity demand by source. Comparing strategies, bottom-up stacking performs better for electricity demand, while both approaches perform similarly for oil demand. Results by demand size suggest that retransformation bias from the log scale (Duan, 1983) and cross-country heterogeneity are particularly important for large economies. Overall, while no single model dominates across all settings, stacking provides a simple and reliable approach to improving forecast accuracy. Originality/value - Our contribution is threefold. First, we provide a systematic comparison of stacking methods for forecasting global energy demand across OECD and non-OECD economies. Second, we evaluate the relative performance of top-down and bottom-up strategies within a common framework. Third, we examine how forecast performance varies with the scale of energy demand, highlighting the role of retransformation bias (Duan, 1983) and cross-country heterogeneity.
- 25 August 2026
- Published by HoChiMinh University of Banking in Asian Journal of Applied Financial Econometrics
- Vol. 1 (2) , 24-47
Open AccessShort-term predictions for country-level energy demand with top-down and bottom-up stacking
Purpose - This paper examines whether stacking (Wolpert, 1992) improves short-term forecasts of global oil consumption and electricity demand during periods of major shocks, including COVID-19, geopolitical conflicts, and trade disruptions. Given diverging trends between OECD and non-OECD economies, we evaluate forecast performance separately across these regions. Design/methodology/approach - We combine XGBoost, random forest, elastic net, multi-layer perceptron, and a unit fixed-effects model within a stacking framework using a non-negative OLS meta-learner. We implement both a top-down approach, which models aggregate demand directly, and a bottom-up approach, which models disaggregated components and aggregates predictions, to assess the value of decomposition. Findings - We find that stacking provides a robust benchmark, consistently matching or outperforming the best individual learner across most specifications. In the top-down setting, stacking generally delivers the strongest performance, particularly for global and non-OECD oil demand and global electricity demand. Bottom-up stacking improves accuracy for most oil sub-aggregates and performs comparably to the best base learner for electricity demand by source. Comparing strategies, bottom-up stacking performs better for electricity demand, while both approaches perform similarly for oil demand. Results by demand size suggest that retransformation bias from the log scale (Duan, 1983) and cross-country heterogeneity are particularly important for large economies. Overall, while no single model dominates across all settings, stacking provides a simple and reliable approach to improving forecast accuracy. Originality/value - Our contribution is threefold. First, we provide a systematic comparison of stacking methods for forecasting global energy demand across OECD and non-OECD economies. Second, we evaluate the relative performance of top-down and bottom-up strategies within a common framework. Third, we examine how forecast performance varies with the scale of energy demand, highlighting the role of retransformation bias (Duan, 1983) and cross-country heterogeneity.
- 2 June 2024
- Published by Springer Nature
- p. 109-129
Using Machine Learning Methods to Estimate the Gender Wage Gap
- 2 June 2024
- Published by Springer Nature
- p. 109-129
Using Machine Learning Methods to Estimate the Gender Wage Gap
- Open Access
ddml: Double/debiased machine learning in Stata
We introduce the package ddml for Double/Debiased Machine Learning (DDML) in Stata. Estimators of causal parameters for five different econometric models are supported, allowing for flexible estimation of causal effects of endogenous variables in settings with unknown functional forms and/or many exogenous variables. ddml is compatible with many existing supervised machine learning programs in Stata. We recommend using DDML in combination with stacking estimation which combines multiple machine learners into a final predictor. We provide Monte Carlo evidence to support our recommendation.
Open Accessddml: Double/debiased machine learning in Stata
We introduce the package ddml for Double/Debiased Machine Learning (DDML) in Stata. Estimators of causal parameters for five different econometric models are supported, allowing for flexible estimation of causal effects of endogenous variables in settings with unknown functional forms and/or many exogenous variables. ddml is compatible with many existing supervised machine learning programs in Stata. We recommend using DDML in combination with stacking estimation which combines multiple machine learners into a final predictor. We provide Monte Carlo evidence to support our recommendation.
- 31 October 2023
- Published by Springer Nature
- p. 131-149
Stacking Regression for Time-Series, with an Application to Forecasting Quarterly US GDP Growth
- 31 October 2023
- Published by Springer Nature
- p. 131-149
Stacking Regression for Time-Series, with an Application to Forecasting Quarterly US GDP Growth
- Open Access
pystacked: Stacking generalization and machine learning in Stata
pystacked implements stacked generalization (Wolpert, 1992) for regression and binary classification via Python's scikit-learn. Stacking combines multiple supervised machine learners -- the "base" or "level-0" learners -- into a single learner. The currently supported base learners include regularized regression, random forest, gradient boosted trees, support vector machines, and feed-forward neural nets (multi-layer perceptron). pystacked can also be used with as a `regular' machine learning program to fit a single base learner and, thus, provides an easy-to-use API for scikit-learn's machine learning algorithms.
Open Accesspystacked: Stacking generalization and machine learning in Stata
pystacked implements stacked generalization (Wolpert, 1992) for regression and binary classification via Python's scikit-learn. Stacking combines multiple supervised machine learners -- the "base" or "level-0" learners -- into a single learner. The currently supported base learners include regularized regression, random forest, gradient boosted trees, support vector machines, and feed-forward neural nets (multi-layer perceptron). pystacked can also be used with as a `regular' machine learning program to fit a single base learner and, thus, provides an easy-to-use API for scikit-learn's machine learning algorithms.
- 30 July 2022
- Published by Springer Nature
- p. 7-29
An Introduction to Stacking Regression for Economists
- 30 July 2022
- Published by Springer Nature
- p. 7-29
An Introduction to Stacking Regression for Economists
- Open Access
- 29 May 2022
- Published by Springer Nature
- p. 133-146
What’s Wrong with How We Teach Estimation and Inference in Econometrics? And What Should We Do About It?
- 29 May 2022
- Published by Springer Nature
- p. 133-146
Open AccessWhat’s Wrong with How We Teach Estimation and Inference in Econometrics? And What Should We Do About It?
- 6 August 2020
- Published by Springer Nature
- p. 23-52
Using Machine Learning Methods to Support Causal Inference in Econometrics
- 6 August 2020
- Published by Springer Nature
- p. 23-52
Using Machine Learning Methods to Support Causal Inference in Econometrics