Mahshid Ahmadian profile

Hello! 👋

My name is Mahshid Ahmadian.

I am currently a Virginia Sea Grant Research Fellow and a Ph.D. candidate in Systems Modeling and Analysis (Statistics and Data Science) in the Department of Statistical Sciences and Operations Research at Virginia Commonwealth University. I have a Master's degree in Economical and Environmental Statistics.

I have a passion for solving complex, real-world problems through statistical modeling, machine learning, and high-performance computing (HPC). My expertise spans Bayesian statistics, spatiotemporal modeling, predictive analytics, and statistical computing, allowing me to work across environmental science, healthcare, technology, and finance. With extensive experience in statistical consulting, I have guided individuals and organizations through challenging academic and industrial problems, demonstrating my ability to extract insights from any dataset, regardless of complexity or field.

LinkedIn Email Me

Technical Expertise

Research

Mahshid presenting research data science
  • Develop a predictive modeling framework for movement data (PhD Thesis)
    • Developed stochastic and Bayesian predictive models to impute and predict locations in movement trajectories. Methodologies included predictive sampling, MLE and Bayesian inference, and hybrid MCMC algorithms of Metropolis-Hastings, Gibbs sampling implemented with HPC, and RC++ for efficient computation. A prototype web tool was also developed to make model outputs accessible for ecological research and fisheries management.
    * This project is funded by Virginia Sea Grant through a two-year competitive fellowship awarded to Mahshid Ahmadian, and supervised by Dr. Edward Boone (Virginia Commonwealth University), and Dr. Grace Chiu (Virginia Institute of Marine Science).
  • Modeling clinical longitudinal ordinal data (Master’s Thesis)
    • Designed and implemented advanced statistical models for analyzing longitudinal ordinal data for a clinical study on migraine patients. The methodology combined mixed-effects modeling with ordinal link functions and incorporated appropriate strategies to handle data gaps and excess variability link.
  • Modeling continues response variable using SAS software (Undergrad Research)
    • During my undergraduate research, I focused on a broad range of statistical modeling techniques using SAS software, including regression analysis and experimental design. The project emphasized learning and applying various modeling approaches within SAS, strengthening my skills in both statistical theory and software implementation link.

About My Current Project

As part of my current project, I am working on several advanced initiatives. One key focus is developing a new predictive model for imputing and predicting geospatial data, which will help improve the accuracy of our spatial analyses. I am also creating a web-based tool to support data-driven decision-making in fisheries management, enabling stakeholders to make more informed choices based on real-time data. To handle the computational demands of these tasks, I am optimizing large-scale models using High-Performance Computing (HPC) and parallelization techniques to ensure efficiency and scalability. Additionally, I am leveraging Rcpp to integrate efficient C++ implementations within R, which significantly accelerates our computations and enhances overall performance.

Awards and Honors

Education

Publications

Leadership and Community Engagement