About the Statistics Department

The Department of Statistics at Texas A&M University is nationally and internationally renowned for its outstanding research in numerous areas of Bayesian statistics, encompassing foundational theory, innovative methodological and algorithmic advancements, and impactful real-world applications. Key strength areas include Bayesian approaches to scientific machine learning, uncertainty quantification, hypothesis testing and model selection, semiparametric/nonparametric modeling and inference, measurement error modeling, causal learning, analysis of structured high-dimensional data, spatial statistics, time series analysis, networks and other dependent data, design and convergence analysis of Markov chain Monte Carlo (MCMC), sequential Monte Carlo (SMC), and variational Bayesian (VB) algorithms and interplay between their statistical and algorithmic properties, decision theory, and quantum algorithms. Faculty collaborate broadly on applying Bayesian methods to cutting-edge applications with researchers across the College of Arts and Sciences, College of Engineering, Mays Business School, and College of Agriculture and Life Sciences.

The department is dedicated to developing novel statistical, computational, and AI methodologies for large-scale and high-throughput data in the highly interdisciplinary field of bioinformatics. It houses the Center for Statistical Bioinformatics and administers the Bachelor of Science degree in Bioinformatics. The department maintains close partnerships and seamless collaborations with the Departments of Biology and Biomedical Engineering, as well as the Colleges of Agriculture & Life Sciences and Medicine. Faculty expertise spans single-cell (multi)omics, spatial transcriptomics, Mendelian randomization for causal inference, neuroimaging, microbiome, digital health, immunotherapy, and cancer genomics.

The Department of Statistics at Texas A&M University advances the foundations and practice of modern machine learning and artificial intelligence through cutting-edge statistical research that emphasizes both methodological rigor and real-world impact. The department plays a leading role in the Texas A&M TRIPODS Research Institute for Foundations of Interdisciplinary Data Science (FIDS), an NSF-funded institute dedicated to advancing interdisciplinary research in data science. Our faculty develop principled approaches for causal learning, high-dimensional and structured data analysis, network learning, probabilistic and scalable Bayesian modeling, reinforcement learning, and uncertainty quantification. We further contribute advanced methodologies and theories in nonconvex and stochastic optimization, tensor and functional data analysis, variational inference, and other core areas of ML/AI, enhancing statistical validity and computational efficiency in complex learning problems. In parallel, faculty lead high-impact interdisciplinary collaborations that leverage and advance ML/AI techniques to tackle real-world scientific challenges. Applications span digital and precision health, ecological behavior modeling, environmental and spatiotemporal systems, genomics and single-cell omics, neuroimaging and brain connectomics, and social networks.

The department advances interpretable, uncertainty-aware statistical neuroimaging across multiple imaging modalities, including structural MRI, functional MRI, diffusion MRI, and EEG/MEG. Development of statistical methods for image-on-image prediction, multilayer and time-varying brain-network models that link connectivity to cognition and disease, and spatial/space-time frameworks, is paired with scalable algorithms for consortia-scale data. By fusing images, networks, and behavior, the department delivers insights with calibrated uncertainty and reliable biomarkers for cognitive aging and neurological disorders, in collaboration with experts across neuroscience, psychology, and public health.

The Department of Statistics at Texas A&M University has established a strong national and international reputation in spatial and spatio-temporal statistics. Faculty develop innovative theories, methodologies, and computational tools for addressing challenges in analyzing large and complex spatial and spatio-temporal data. Research strengths include scalable Gaussian process for massive datasets, hierarchical Bayesian modeling, spatial temporal models, spatial data fusion, multiresolution and nonstationary modeling, spatial extremes and rare event analysis, spatial clustering, spatial machine learning models, and spatial causal inference. Applications of these methods address pressing challenges in environmental and climate science, ecology and conservation, energy and natural resource management, epidemiology and public health, urban planning, and agricultural sciences. Emerging application research directions include statistical modeling for spatial transcriptomics and high-dimensional spatial omics data, bridging spatial methodology with modern biological and biomedical applications.

The department develops statistical methods for analyzing data with complex dependencies, including temporal patterns, network structures, and correlated observations. Faculty expertise in time series addresses questions about how systems evolve over time, detecting changes in dynamic processes, analyzing cyclical patterns and trends, and modeling data from wearable devices and monitoring systems. In network analysis, research focuses on understanding community structures in social and biological networks, learning relationships among interconnected variables, analyzing brain connectivity patterns, and modeling information flow in technological systems. The department also advances methods for high-dimensional data with dependencies, large-scale streaming data analysis, and understanding uncertainty in complex systems. Applications span neuroscience and brain imaging, digital health and continuous monitoring technologies, environmental systems, genomic regulatory networks, and social and technological networks.