Quantitative Research, Applied Statistics, and Machine Learning

I am a mathematics professor with graduate training in mathematics and applied statistics. My work sits at the intersection of teaching, learning, student success, quantitative methods, applied research, statistical modeling, machine learning, and clear communication of data-driven results.

I am especially interested in projects where rigorous analysis, research design, and practical data science workflows can support better decisions in education, analytics, applied AI, and quantitative research.

Featured Work

Master of Science in Applied Statistics Capstone

A full applied statistics project analyzing public felony case records from Cleveland County, Oklahoma, with attention to sentencing outcomes, attorney type, and related case characteristics. I was responsible for the project design, research questions, data collection, data cleaning, statistical analysis, interpretation, and client-facing communication. Required for completion of the Master of Science in Applied Statistics at the University of Oklahoma

The project required building a usable dataset from public records one observation at a time. Because the data came from real administrative court records rather than a pre-cleaned research dataset, the work required careful coding decisions, judgment about ambiguity, ethical interpretation, and statistical maturity about what could and could not be concluded from observational data.

  • Designed and executed an applied statistical research project
  • Collected and coded real-world public-record data manually
  • Handled ambiguity, exclusions, variable coding, and analytic subsets
  • Used chi-square tests, logistic regression, and random forest feature importance
  • Interpreted observational findings without overstating causality
  • Produced both internal technical and client-facing reports
Client-Facing Report Technical Report Video Presentation

Master's Thesis: Predicting Success on the NCLEX-RN

A graduate-level quantitative research project examining predictors of NCLEX-RN first-time success among associate degree nursing students at a small public university. The project connected student success, educational research, applied statistics, institutional decision-making, and statistical modeling. Required for completion of the Master of Science in Mathematics at Shawnee State University.

This thesis involved a full literature review, a theoretical framework, and analysis of real institutional data with practical complications, including missing values, duplicate records, limited failure cases, and substantial class imbalance. The work required not only fitting models, but also understanding the limits of prediction when the outcome distribution itself makes classification difficult.

  • Completed a full graduate thesis in applied quantitative research
  • Reviewed academic and demographic predictors of NCLEX-RN success
  • Used a theoretical framework related to nursing student retention and success
  • Cleaned and analyzed real institutional education data
  • Handled missingness, duplicate records, and class imbalance
  • Used logistic regression, correlation analysis, group comparisons, and diagnostics in R
View Thesis

End-to-End Machine Learning Deployment

A production-aware machine learning project implementing an end-to-end classification workflow for U.S. visa approval prediction. The project moves beyond notebook-based modeling by organizing the workflow into modular components for data ingestion, validation, transformation, model training, evaluation, prediction, and deployment.

This project was implemented as part of my applied data science and MLOps development. It helped me practice the engineering side of machine learning, including FastAPI application development, Docker packaging, GitHub Actions, AWS deployment concepts, MongoDB integration, and cloud-based model storage.

  • Implemented an end-to-end machine learning classification workflow
  • Built modular training and prediction pipeline components
  • Used FastAPI for prediction serving
  • Practiced Docker-based packaging and deployment structure
  • Worked with MongoDB, AWS/S3 components, and GitHub Actions
  • Strengthened production-aware ML and MLOps foundations

Teaching, Learning, and Applied Research

My teaching background gives me a strong interest in how people learn quantitative ideas, how data can support better educational decisions, and how statistical methods can be used responsibly in real-world settings.

I am interested in work that connects mathematics education, student success, quantitative methods, applied statistics, machine learning, research design, and decision support.

Research and Education Interests

  • Teaching and learning in mathematics, statistics, and data science
  • Quantitative methods in education
  • Learning analytics
  • Student success research
  • Program evaluation
  • Assessment and measurement
  • Applied statistical consulting

Technical and Analytical Interests

  • Applied statistics
  • Statistical modeling and interpretation
  • Machine learning for decision support
  • Reproducible analysis
  • Data visualization and storytelling
  • Interactive dashboards
  • Production-aware AI/ML workflows

Technical Areas

  • R and RStudio
  • Python
  • Applied statistics
  • Quantitative methods
  • Statistical modeling
  • Logistic regression and classification
  • Data visualization
  • R Markdown and Quarto
  • Git and GitHub
  • Shiny dashboards
  • Machine learning foundations
  • MLOps foundations
  • Research design and evaluation
  • Educational data analysis

Professional Direction

My professional direction is to combine mathematical depth, applied statistical training, teaching experience, research design, communication, and practical data science skills.

I am building toward work involving quantitative research, applied analytics, machine learning, statistical consulting, educational data analysis, program evaluation, decision support, and production-aware AI/ML systems.

The strongest version of my work sits at the intersection of rigorous analysis, clear explanation, human learning, applied modeling, and practical systems that help people and organizations make better decisions.