StatsPAI: Agent-Native Causal Inference & Econometrics

StatsPAI is the agent-native Python package for causal inference and applied econometrics. One import statspai as sp, 390+ functions, covering the complete empirical research workflow.

Source: https://github.com/brycewang-stanford/StatsPAI PyPI: pip install statspai Paper: Published in Journal of Open Source Software (JOSS)

Why StatsPAI for Agents?

StatsPAI is the first econometrics toolkit purpose-built for LLM-driven research workflows:

1. Self-describing API: sp.list_functions(), sp.describe_function("did"), sp.function_schema("rdrobust") — agents can discover and understand functions without documentation lookup
2. Unified result objects: Every function returns a CausalResult with .summary(), .plot(), .to_latex(), .to_word(), .to_excel(), .cite()
3. One import: No need to juggle 20+ packages — import statspai as sp covers everything
4. Publication-ready output: Word, Excel, LaTeX, HTML export in every function

Core Methods