Stijn Conix

I provide rigorous decision support for companies, researchers, and public agencies working with complex data. My work is grounded in peer-reviewed research, with a background spanning Bayesian statistics, causal inference, biodiversity science, philosophy of science, and digital humanities.

I focus on structured, typically causal models that make assumptions explicit and results interpretable, rather than purely predictive or black-box approaches. Across domains — from marketing effectiveness and experimentation to research evaluation and policy analysis — my aim is to produce analyses that are transparent, reproducible, and decision-relevant.

For Academics:

• Experiment design and power analysis
• Support in responsible research practices (preregistration, open data, reproducible code)
• Visualizing and communicating statistical results
• Writing methodology and results sections

For Businesses:

• Design, implementation, and interpretation of experiments (A/B testing and more advanced designs)
• Marketing mix modelling (MMM) and marketing analytics
• Causal analysis of experimental and observational data
• Data-driven decision making under uncertainty (quantifying and incorporating uncertainty into decisions)

I approach applied problems with the same standards I use in academic research: explicit assumptions, transparent modelling choices, and careful treatment of uncertainty. Rather than chasing single best estimates, I prioritise robustness, sensitivity to assumptions, and the limits of what the data can support.