Research

SUBMITTED MANUSCRIPTS

• Mitchell Roznik, Ashok K. Mishra, Hongqiang Yan. Field Rotation Related Soil Productivity Changes, Yield Risk, and Efficiency in Crop Insurance Rating. (Revise and resubmit, American Journal of Agricultural Economics)

• Hongqiang Yan, Serkan Aglasan, Le Chen, Roderick Rejesus. The Dual Damage from Soil Erosion: Lower Yields and Higher Risk in US Agriculture. (Under Review, American Journal of Agricultural Economics)
  Latest version

WORKING PAPER

• Jiatong Li, Hongqiang Yan. Uniform Inference in High-Dimensional Threshold Regression Models. (Co-first authored).
  Latest version

  Abstract: We develop a uniform inference theory for high-dimensional slope parameters in threshold regression models, allowing for either cross-sectional or time-series data. We first establish oracle inequalities for prediction errors and ℓ1 estimation errors for the Lasso estimator of the slope parameters and the threshold parameter, accommodating heteroskedastic non-subgaussian error terms and non-subgaussian covariates. Next, we derive the asymptotic distribution of tests involving an increasing number of slope parameters by debiasing (or desparsifying) the Lasso estimator in cases with no threshold effect and with a fixed threshold effect. We show that the asymptotic distributions in both cases are the same, allowing us to perform uniform inference without specifying whether the model is a linear or threshold regression. Additionally, we extend the theory to accommodate time-series data under the near-epoch dependence assumption. Finally, we demonstrate the consistent performance of our estimator in both cases through Monte Carlo simulations, and we apply the proposed estimator to empirical analyses of cross-country economic growth rates and the effect of a military news shock on U.S. government spending.
  Supplementary Material

• Hongqiang Yan, Barry Goodwin, Mehmet Caner. Global Maize Market Integration: A High-Dimensional Local Projection Approach with Mixed-Frequency Data and Regime Switching.
  (Available upon request)

  Abstract: This paper investigates the degree of market integration, exchange rate pass-through, and the market factors that contribute to deviations from perfect integration. To analyze the price linkage dynamics, we apply the novel debiased LASSO for Local Projection Approach, including linearity testing within high-dimensional Regime Switching regression models. Our findings reveal significant global maize market integration, particularly when incorporating threshold effects and key market factors. Notably, consumer prices and unemployment emerge as important determinants of price linkages, underscoring their relevance in the global commodity market.

• Hongqiang Yan, Ashok K. Mishra, Jaweriah Hazrana. Spatial Analysis of Modern Rice Varieties Technology on Production: Evidence from Panel Data in Bangladesh.

  Abstract: Although modern rice varieties have the potential to enhance yields, their adoption among smallholder farmers in Bangladesh remains limited. Many farmers continue to favor inbred high-yielding or traditional local rice varieties, despite their suboptimal productivity. However, there is a lack of research examining how the adoption of modern rice varieties influences productivity in developing nations. This study explores this relationship by incorporating village- and location-specific heterogeneity in production technology within an advanced econometric framework. Using data from the Bangladesh Integrated Household Survey, we analyze spatial heterogeneity by integrating geographical coordinate information with a household-level panel dataset on rice production and technology adoption. Furthermore, we develop and estimate a location-dependent production function incorporating Hicks-neutral productivity. The findings reveal that the productivity impact of improved seed varieties is highly variable, primarily influenced by spatial characteristics rather than the specific rice variety type. These results underscore the crucial role of spatial factors in the adoption of modern rice varieties in Bangladesh and highlight important policy implications for optimizing resource and financial allocations to promote the adoption of improved agricultural technologies and support sustainable agricultural development in emerging economies.

• Hongqiang Yan, Mark Manfredo, Ashok K. Mishra. Machine Learning Forecasts for Food Price Inflation: Expanding FRED-MD.

  Abstract: In recent years, U.S. food prices have surged amid supply chain disruptions, labor shortages, rising input costs, and global shocks such as COVID 19 and the war in Ukraine. Because of this, there is renewed interest in forecasting food price inflation by economists, policymakers, and agribusiness firms alike. This study leverages machine learning methods and the availability of large economic databases to improve forecasts of U.S. food price inflation. We show that forecasts generated from machine learning models incorporating a large set of covariates—particularly using a modified version of the FRED-MD dataset—are more accurate than univariate benchmark forecasts over several alternative horizons. Notably, forecast combination strategies that combine forecasts generated from different machine learning methods as well simplistic univariate models often outperform forecasts generated from individual models and therefore warrant greater attention.

• Mitchell Roznik, Ashok K. Mishra, Hongqiang Yan. Extreme Climate, Financial Health, and Credit Default Risk: An American Landscape.

  Abstract: Climate change is expected to increase the frequency and severity of drought in the United States. This study investigates the effect of drought conditions on farm credit default risk and examines the vulnerability of farms to enhanced drought risk. We use individual-level data from Farm Service Agency loan data covering seven-year operating loans. The study applies Cox proportional hazard and Generalized Gamma parametric survival models with various established financial health variables and drought. Findings suggest that lagged drought conditions, occurring in the growing season before loan origination, significantly increase the probability of default. A drought-affected borrower is about 11% more likely to default than an equivalent borrower who has not experienced drought. Non-white and Hispanic farmers affected by drought have higher default risks than their counterparts. Similarly, small and medium-sized farms, compared to large farms affected by drought, exhibit higher loan risk. These findings have important implications for lenders and policymakers, emphasizing the need for comprehensive risk assessment strategies that account for financial, demographic, and environmental factors in the agricultural sector.

WORK IN PROGRESS

• Hongqiang Yan Data-Driven Estimates of Structural Change in the Demand for Multiple Peril Crop Insurance.

• Hongqiang Yan, Ashok K. Mishra, Xi Zhou. Examining the Role of Spatial Heterogeneity in Productivity-Enhancing Activities: Evidence from the Chinese Food and Beverage Sector.