This applied statistics project connects your organization with upper-year undergraduate students trained in data science and multivariate analysis. Students will use advanced statistical techniques and machine learning algorithms to uncover actionable insights from a dataset you provide.

Working in small, self-assigned teams, students will apply techniques such as Principal Component Analysis (PCA), clustering, and discriminant analysis to explore data patterns, reduce dimensionality, and identify drivers of key outcomes. The focus is on real-world application and communication of findings in a clear, stakeholder-ready format.

Student Capabilities

Pre-existing skills:

• Statistical computing and data visualization in R
• Matrix algebra and multivariate statistical foundations
• Data cleaning, wrangling, and exploratory analysis

Skills developed through the project:

• Principal Component and Factor Analysis
• Discriminant and Cluster Analysis
• Canonical Correlation
• Machine Learning Applications (e.g., classification, unsupervised learning)
• Executive communication and stakeholder storytelling
• Team-based project management

How Students Will Support Your Organization

Students will:

• Analyze a clean, pre-prepared dataset provided by your organization
• Apply multivariate and machine learning methods to uncover patterns, trends, and relationships
• Visualize results using compelling charts and summaries in R
• Translate complex findings into clear, actionable insights for non-technical stakeholders
• Work collaboratively with you to ensure alignment on project goals and outcomes

Time Commitment

• 25 hours per student (approx. 100 hours per team of 4)
• Minimal lift for your organization:
• Provide a clean dataset and brief background at project start
• Optional mid-point check-in
• Attend final presentation and offer feedback

Insightful final report with visualizations, key findings, and practical recommendations

Presentation deck and 10-minute summary presentation for stakeholders

Code appendix (in R) with reproducible analysis