Grace Siliki

About Grace Siliki

I am an Applied Statistician with a master’s degree from Michigan Technological University and a strong foundation in statistical modeling, data analysis, and research-driven problem solving. My work centers on transforming complex datasets into meaningful insights through rigorous quantitative methods and structured analytical workflows.My technical expertise includes regression modeling, generalized linear models, predictive modeling, multivariate analysis, nonlinear regression, Monte Carlo integration, and quantifying predictor importance. I work extensively with R and Python for statistical computing, as well as SPSS, SAS, SQL, and LaTeX for data analysis, reporting, and reproducible research.Through roles as a Research and Teaching Assistant and Data Analyst, I have applied advanced statistical techniques to real-world datasets, ensuring data integrity through cleaning, preprocessing, outlier detection, and missing-data handling. My analytical experience spans statistical modeling, predictive analytics, hypothesis testing (parametric and non-parametric methods), stratified sampling optimization and data-driven problem solving across diverse and complex datasets.I am particularly interested in roles that leverage statistical modeling, research design, and data science to inform evidence-based decision-making. My long-term goal is to contribute to impactful quantitative research at the intersection of statistical theory and applied analytics.

Experience

1. Research and Data Analyst

   Statistics Without Borders

   Jan 2026 — Present

   Contribute to a global health research initiative analyzing pediatric malnutrition and hospitalization risk using large-scale clinical datasets observations,~195 variables)Clean, validate, and prepare structured health data in R, implementing systematic quality checks for missingness, outliers, duplicates, and inconsistent categorical valuesDevelop reproducible data cleaning and documentation workflows using Quarto, ensuring transparency and auditability of all preprocessing stepsIdentify and flag data quality issues using structured tagging systems (e.g, unreliable_entry) to support downstream analysis and decision-makingCreate exploratory visualizations and summary statistics to uncover trends in child health outcomes and inform preliminary risk factor analysisCollaborate with an international, multidisciplinary team to translate data findings into actionable insights for public health interventions

Education

• Michigan Technological University

  Master's degree, Applied statistics

• Kwame Nkrumah University of Science and Technology, Kumasi

  Bachelor of Science - BS, Statistics