Non Technical Summary
In response to the growing need for agricultural economists trained to harness the data revolution, we aim to train seven NFF Fellows in the newly developed MS data science program with a specialization in "Applied Economics and Predictive Inference." The proposed program is specifically tailored toward the needs and challenges associated with big data in agricultural markets and economics. The NNF Fellows will be trained in the methods and applications of computational statistics to answer questions critical to agriculture and food production. The program will offer several opportunities for professional development. Backed by rigorous training in applied economics, the fellows will specialize in the theory and application of data science concepts and methods. The proposed MS specialization integrates well with the existing MS programs in data science and agricultural and resource economics and is a critical educational initiative of the University of Connecticut, benefiting from interdisciplinary collaboration and a highly diverse and multicultural research and education environment. The program will allow the NNF Fellows from underrepresented groups to engage with future employers through experiential learning and collaboration in research projects. Accompanied by thorough assessments and follow-ups, the education program will add seven truly outstanding agricultural economists trained in "Data Science, Applied Economics, and Predictive Inference" to critical niches in academics, industry, and government. The project will also develop new knowledge on data science in agricultural and resource economics, foster the programmatic development of the "Applied Economics and Predictive Inference" specialization, and disseminate the outcomes to the academic community and public.

Classification

Knowledge Area (KA)	Subject of Investigation (SOI)	Field of Science (FOS)	Percent
603	6199	3010	50%
901	6199	2090	50%

Knowledge Area
603 - Market Economics; 901 - Program and Project Design, and Statistics;

Subject Of Investigation
6199 - Economy, general/other;

Field Of Science
2090 - Statistics, econometrics, and biometrics; 3010 - Economics;

Goals / Objectives
We will train seven USDA National Needs Fellows (NNF) in a newly established and highly interdisciplinary MS program in "Data Science, Applied Economics, and Predictive Inference" at the University of Connecticut. The proposed activities address the Targeted Expertise Shortage Area of "Agricultural Markets and Economics" and contribute to the USDA mission under discipline code M "Agricultural Marketing and Management (includes Agricultural Economics)."

Project Methods
The seven NNF Fellows will join an interdisciplinary MS program in "Data Science, Applied Economics, and Predictive Inference"established in Fall 2023 that will close a gap in the education and training of agricultural economists in the United States. The combination of applied economics and data science will enable the NNF Fellows to pursue careers in the agricultural and food sciences that requireadvanced data science skills and a solid understanding of economic conceptsin the TESA "Agricultural Markets and Economics." The program builds on a philosophy of putting experiential learning at the center of the education and training experience. The goals of the program are to provide students withexpertise in five core technical competency areas:Microeconomics: A solid understanding of microeconomic theory and its application to research questions in the agricultural and food sciences is crucial for the professional success of the NNF Fellows.Statistics: A holistic understanding of statistics is vital for data scientists. NNF Fellows will become familiar with statistical tests, distributions, maximum likelihood estimators, etc. This knowledge will also be needed for machine learning. Still, one of the more critical aspects of the analytical skillset is understanding when different techniques are valid. Statistics is essential for various agricultural and food sciences fields, especially for data-driven fields such as agricultural and resource economics.Programming: The professional command of a programming language is a pivotal skill set. This skillset includes solid knowledge of a statistical programming language, like R or Python, and a database querying language such as SQL.Machine learning: The understanding of machine learning concepts and the ability to apply them to fundamental questions in the economics of agriculture and food sciences is a pivotal set of abilities. NNF Fellows will be able to improve the predictive performance and optimize algorithms to answer fundamental and applied research questions in agricultural and resource economics.Data visualization and communication: Communicating data is critical, especially for agriculture and food production economics. When it comes to communicating data, this means the ability to describe findings and the way techniques work to audiences, both technical and non-technical. Visualization-wise, NNF Fellows will become familiar with data visualization dashboarding tools. It is essential to be familiar with the tools necessary to visualize data and the principles behind visually encoding data and communicating information.These competencies will be obtained through formal coursework, internal and external internships, and research experiences at the interlink between data science and agricultural and resource economics. Each NNF Fellow will be required to obtain at least 36 credits in the "Data Science, Applied Economics, and Predictive Inference"program.