PhD in Statistics · Causal Inference · Teaching and applied consulting
English (en) · Español (es)
Applied statistician working where causal inference meets production systems: estimating effects, stating assumptions, and keeping results reproducible, rather than only predicting. I direct the Center for Causal Inference at the Universidad Nacional de Ingeniería (UNI), Peru, teach at graduate level, and advise organizations on impact evaluation and statistical modelling.
repositorio-forecasting-data-science
A professional, reproducible course on forecasting and MLOps: eight real datasets, eight notebooks run end to end, a 122-page monograph and an interactive presentation. The course's thesis is explicit and documented experiment by experiment: complexity does not guarantee improvement; in four of the eight experiments the naive baseline (seasonal naive, ETS) matches or is only barely beaten by the sophisticated model.
sistemas_inteligencia_causal_estudiante
ECO-490 / ECON-540 (2026). Sixteen weeks and 32 sessions split 50% theory / 50% production. Monorepo with a 32-chapter monograph, Series A notebooks (case studies) and Series B (production), 27 labs and a final project. The focus is effect estimation with machine learning together with system engineering; the Hugging Face layer is optional and everything runs locally.
Master's programme in Statistical Science and Engineering, UNI. Unifying framework: the Geometry of Statistical Causality (GCE), with the master chain |ATE| ≤ W₁ ≤ W^{G,1}. Thirty-two chapters, 32 notebooks, a PDF book and a Jupyter Book. Working principle Proofs-to-Python: every proven bound is checked with assert, seed 42, and mandatory validation of assumptions.
- Statistical programming with R — statistical programming in R.
- Teoría Estadística aplicada a agentes estadísticos — foundations of statistical theory for agents.
- Probability distributions with R (Shiny) — interactive teaching app.
- Programa Adulto Mayor, Instituto Teodoro Wickel — causal study of quality of life and health based on national surveys. Case
- Physical activity in schoolchildren — multinomial logistic model comparing groups of students. Analysis
- PM2.5 particulate matter in Temuco — comparison of statistical and machine-learning models for prediction. Project
Director of the Center for Causal Inference, Universidad Nacional de Ingeniería (UNI), Peru. Research lines: applied causal inference, impact evaluation, causal intelligence systems, and graduate training in statistics.
- LinkedIn: jaime-lincovil-curivil
- GitHub: @jelincovil
- Location: Chile