Skip to content
Demonstrator · items marked Example are invented · what exists today
E2ER

External pipelines · RISE project catalogue

StatsPAI

An "agent-native" Python library for causal inference and applied econometrics — a Stata/R-replacement workbench (regress, ivreg, feols, Callaway-Sant'Anna DiD, rdrobust, synthetic control, matching, DML, meta-learners, causal forests, structural estimation; 1,145 registered functions across 87 submodules) whose structured result objects, machine-readable schemas, and MCP server are designed for LLM agents to call. Sits in the infrastructure-for-pipelines layer of RISE, like ToolUniverse, not a research pipeline itself.

Indexed in RISE · activeConformance with the standard plannedProject site

What it does

The catalog's clearest case of tooling redesigned *for* agents rather than agents wrapped around tooling: one `import statspai as sp` entry point, `.to_agent_summary()` / `.to_latex()` / serialization on every result object, an MCP server, and a validation-tiered registry that records per-estimator R/Stata reference-parity status separately from API breadth — explicitly so that surface area is not passed off as validation evidence.

Focus
analysis
Inputs
user-dataset, model-formula
Outputs
estimation-results, publication-tables, figures
Maintained by
Biaoyue (Bryce) Wang (Stanford REAP); Scott Rozelle (Stanford REAP)
Started
2025

Description

Data model
Discipline
Economics
Method family
not specified
Design
not specified
Research stage
Data analysis
Contributors
Biaoyue; Scott Rozelle
Usage
not used in published research yet
Source
RISE project catalogue · projects/landscape · @4c17bae
Record
pipeline:statspai · JSON

Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.

Bring it into the standard

A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.

Other pipelines in Economics