Problem
A climate-finance research organisation needed to quantify the impact of specific policy interventions on capital flows and emissions — separating the policy signal from confounding macro factors, sector trends, and pre-existing trajectories.
Approach
Applied causal inference and econometric methods to isolate the policy effect. Difference-in-differences design where treatment timing was identifiable, synthetic control for policies without natural comparison groups, robustness checks against alternative explanations. Output structured for both policy audiences (executive summary, single-chart impact framing) and academic audiences (full methodology, sensitivity analysis, replication code).
Stack
Python · statsmodels · scikit-learn · econometric specifications · Pandas / NumPy
Outcome
A defensible quantification the client could carry into policy briefings and academic forums alike — same underlying numbers, two presentation registers. The work directly informed downstream policy advocacy.
[CLIENT QUOTE TO ADD — paste the actual testimonial here when ready]
— [Name, Role, Organisation]