Select a replication from the sidebar to view its files
Claude Code Economist
Companion data for Claude Code as an Empirical Economist. 100 independent Claude Code replications for each of three causal-inference tasks from Huntington-Klein et al. (2025).
Research question: Among Hispanic-Mexican immigrants in the US, what was the causal effect of DACA eligibility on full-time employment?
Task 1: Full Freedom
Raw ACS data only. Analysts choose their own research design, sample, and controls.
Task 2: Specified Design
Same data, but the research design is prescribed: compare ages 26–30 (treated) vs. 31–35 (control) in a difference-in-differences framework.
Task 3: Pre-Cleaned Data
Same design as Task 2, plus a pre-cleaned dataset with treatment and outcome variables already constructed.
Select a task, then click a replication to browse its report, run log, and code.
The value next to each rep (e.g. +2.6pp) is the preferred DiD point estimate; use the Sort dropdown to rank.
Badges:
PDF report,
LOG run log,
N PY number of Python code files,
BUG verified coding error affecting the estimate (10 of 300),
RECOVERED code recovered from the run log (19 of 300).
Disclaimer: This website was made by Serafin Grundl (and Claude Code). I am an economist at the Federal Reserve Board. This is my personal website and the analysis and conclusions presented on this website reflect my views and do not indicate concurrence by the Board of Governors or the Federal Reserve System. Contact: serafin.j.grundl@frb.gov