The Lab

Methodology Explorations. Work in Progress.

These are frameworks and prototypes I’m developing — not yet at the maturity bar required for the Studies portfolio (some use real data; the Lab/Studies distinction is about validation depth and decision-grade readiness, not data source). They demonstrate methodology, not findings. When something here matures to real data and validated results, it moves to Studies.

Causal Inference · Bayesian Network

Global Risk Intelligence Network

36 global risks across 6 domains, connected by 101 causal edges. Inject evidence — a pandemic, a cyberattack, a commodity shock — and watch beliefs cascade through the network in real time. Adjust any causal link and see how sensitive your conclusions are to your assumptions.

36 nodes 101 edges 6 preset scenarios Live inference

Higher Education · Two questions, same sector

Risk Modeling · Institutional Survival

College Closure Risk

4,000+ institutions modeled with real College Scorecard and IPEDS data. Six investigations, three model tiers, three interactive tools.

4,000+ institutions 6 investigations 3 model tiers Real IPEDS data

Data Analysis · Program-Level ROI

Is Your Degree Worth It?

65,935 college programs analyzed with real IRS earnings data. 34% have negative lifetime ROI. Five questions from program-level ROI through variance decomposition to policy simulation. Real data, real findings — but data analysis, not modeling and simulation.

65,935 programs 5 investigations 3 interactive tools Real IRS earnings data

More explorations will appear here as I develop new frameworks. For validated analyses with real data, see the Studies.