Statistical Modeling

Statistical modeling research develops and applies quantitative methods to understand complex phenomena and make predictions. Investigations encompass areas such as developing novel techniques for analyzing data with excess zeros, such as in health or environmental monitoring, and creating robust methods for generating realistic synthetic datasets for privacy-preserving analysis. Researchers also explore efficient experimental designs, advanced psychometric models for measurement, and the application of statistical learning, including permutation tests and Bayesian approaches, to diverse data types. The use of statistical programming languages like R is central to these efforts.

This work holds particular relevance for Arkansas by providing tools to analyze data critical to the state's economy and well-being. For example, statistical models can inform agricultural practices by analyzing yield data, aid in public health initiatives by understanding disease prevalence and risk factors, and support environmental management by modeling natural resource trends. Understanding patent data through statistical lenses can also shed light on innovation within Arkansas industries.

This research area benefits from strong interdisciplinary connections, including expertise in zero-inflated data analysis, synthetic data generation, patent data analysis, and experimental design. Engagement spans multiple institutions across Arkansas, fostering collaboration and expanding the reach of statistical expertise.