AI Methods

AI-assisted applied economics research. Each article ships with Python code and replication materials.

Build Your Own Tools: Tutorials

Articles that walk through building research tools, end-to-end. Each pairs with code in our GitHub or with live tools at Tools & Code.

Well-Executed But Not Important: Reading Importance From the Published Record

An LLM classification of 2,493 health-economics articles to operationalize importance. Calibration is 35% of publications but 18% of citations; Identification carries a +91% premium and Reframing +126%, holding topic, journal, and year constant. Pairs with the journal-topic-shares replication repo.

May 2026
meta-research llm-classification citations

Cycling Through Bad Ideas Faster: A Medicaid Branding Worked Example

A two-week solo cycle through three coding rules, a controls ladder, and a behavioral-mechanism test on state Medicaid program branding, ending at a bounded null after expansion-cohort fixed effects collapse a naive +22% headline. Companion to the meta-research piece above.

May 2026
medicaid difference-in-differences ai-workflow

Robustness checks for Medicaid DiD after the 2023 Unwinding

A three-check diagnostic protocol for state Medicaid panels, with a clean replication dataset and worked Callaway-Sant'Anna code.

May 2026
medicaid difference-in-differences callaway-santanna

Claude Code Skills Get Stale. Audit Them Quarterly.

A repeatable audit so the skills, hooks, and memory entries we wrote for older models stop quietly shaping today's numbers.

May 2026
tutorial claude-code

A Pre-Analysis Plan for Your Coding Agent

A three-layer architecture, rule, gate, and verification, for keeping a reasoning agent disciplined when system prompts alone are not enough.

May 2026
tutorial agents

Building a Literature Surveillance System

Combining free tools (Google Scholar, Semantic Scholar) with an AI assistant that handles the glue: citation networks, source merging, and the quiet failures.

April 2026
tutorial literature review

One Context File, Zero Re-Explanations

How we set up a CLAUDE.md context file so research context survives across sessions, and we stop re-explaining the same project every time.

October 2025
tutorial claude-md

From Methods Paragraph to Working Pipeline

Translating a methodology section into executable code with AI assistance, step by step.

October 2025
tutorial workflow

47 Scripts to 15: Cleaning a Research Codebase

Using an AI assistant to refactor and consolidate a sprawling research codebase without losing the analytical thread.

November 2025
tutorial refactoring

6,613 Stores, $147, Zero Lost Data

Building resilient data pipelines that handle API failures, rate limits, and edge cases without losing rows.

November 2025
tutorial api

400 Labels to 94% Accuracy

Building and validating a grocery store classifier through iterative labeling, with the loop documented end-to-end.

October 2025
tutorial validation

EBT Verification Methodology

Cross-validating SNAP retailer data against multiple authoritative sources, so the labels we trust have a paper trail.

October 2025
tutorial validation

How to Calculate 2.7M Transit Routes for Free

Step-by-step guide to r5py, GTFS data, and multimodal accessibility analysis at zero cost.

November 2025
tutorial r5py GTFS

Most Recent

Well-Executed But Not Important: Reading Importance From the Published Record

When AI thins out the technical-flaws desk-rejection pretext, editors will have to learn to say "well-executed but not important" on the record. We classify 2,493 articles across four health-economics journals to ask what "important" has actually meant.

May 2026
meta-research citations llm-classification

Cycling Through Bad Ideas Faster: A Medicaid Branding Worked Example

What AI actually adds to solo research is fast iteration through ideas that turn out to be wrong, with new techniques sometimes emerging as byproducts of the failed attempts.

May 2026
medicaid difference-in-differences ai-workflow

Claude Code Skills Get Stale. Audit Them Quarterly.

Every skill, hook, and memory entry written for an older model is a patch with an expiration date. In empirical research, the expired ones produce wrong numbers that look right and shape the policy decisions built on them.

May 2026
claude-code research-workflow reproducibility

What AI Impact Looks Like in the Slow Data

Usage telemetry sees AI adoption; slow public data sees household conditions. The same AI tooling can read both at the cadence either one needs.

May 2026
ai-impact data-monitoring

A Pre-Analysis Plan for Your Coding Agent

A three-layer architecture for keeping reasoning agents disciplined: rule, gate, and verification. Trained priors beat system prompts, so reliable behavior redirection needs architecture, not instruction.

May 2026
agents verification

Building a Literature Surveillance System

Free tools like Google Scholar alerts and Semantic Scholar already monitor academic literature. What an AI coding assistant adds is the glue: combining sources, following citation networks, and catching the quiet failures that make AI-gathered references dangerous.

April 2026
literature review skills

Browse all 53 methodology articles by category below.

Medicaid Fraud Detection

What 227 Million Rows of Medicaid Data Can and Can't Tell Us

The largest Medicaid dataset in history just went public. What it contains, what's missing, and why that matters for fraud screening.

February 2026
T-MSIS data quality

The Label Problem: Why Fraud Labels Are Harder Than They Look

Exclusion lists are the closest thing we have to fraud labels. They are further from ground truth than most analysts assume.

February 2026
LEIE labels

What Billing Patterns Actually Look Like

Comparing excluded and non-excluded providers across billing volume, coding concentration, and temporal patterns.

February 2026
billing analysis peer groups

Can a Classifier Find What Simpler Methods Miss?

Building a supervised fraud classifier with gradient boosting, SHAP interpretation, and honest temporal validation.

February 2026
machine learning SHAP

AI-Assisted Research

Well-Executed But Not Important: Reading Importance From the Published Record

An LLM classification of 2,493 health-economics articles to operationalize importance. Calibration is 35% of publications but 18% of citations; Identification carries a +91% premium and Reframing +126%, holding topic, journal, and year constant.

May 2026
meta-research llm-classification citations

Cycling Through Bad Ideas Faster: A Medicaid Branding Worked Example

A two-week solo cycle through three coding rules, a controls ladder, and a behavioral-mechanism test, ending at a null. What AI compresses is the calendar time of discarding bad ideas.

May 2026
medicaid difference-in-differences ai-workflow

One Context File, Zero Re-Explanations

How CLAUDE.md files maintain research context across sessions, eliminating repetitive explanations.

October 2025

From Methods Paragraph to Working Pipeline

Translating a methodology section into executable code with AI assistance.

October 2025

47 Scripts to 15: Cleaning a Research Codebase

Using AI to refactor and consolidate a sprawling research codebase.

November 2025

Data Collection & Validation

6,613 Stores, $147, Zero Lost Data

Building resilient data pipelines that handle API failures, rate limits, and edge cases.

November 2025

400 Labels to 94% Accuracy

Building and validating a grocery store classifier through iterative labeling.

October 2025

EBT Verification Methodology

Cross-validating SNAP retailer data against multiple authoritative sources.

October 2025

Spatial Analysis

How to Calculate 2.7M Transit Routes for Free

Step-by-step guide to r5py, GTFS data, and multimodal accessibility analysis.

November 2025
tutorial r5py GTFS

Residualized Accessibility Index

Separating transit access from confounding factors using regression residuals.

November 2025

Frequently Asked Questions

What is AI-assisted research?

AI-assisted research uses large language models like Claude to accelerate the translation of methodological expertise into working code. The researcher provides domain knowledge, variable definitions, and methodological decisions through context files (CLAUDE.md). The AI helps implement these ideas as code, identifies edge cases, and assists with refactoring. AI assistance doesn't replace expertise; it multiplies its impact. See our article on context files in research.

How do you calculate transit accessibility for free?

We use r5py, a Python library built on Conveyal's R5 routing engine. Combined with publicly available GTFS transit feeds, it can calculate millions of multimodal routes at zero cost. Our r5py tutorial walks through the complete process with working code examples.

How do you validate data quality?

We cross-validate against multiple authoritative sources. For grocery store data, we compared USDA Food Access Atlas listings against the official SNAP retailer database, California ABC license records, and manual verification. This iterative process, documented in our grocery store classifier article, achieved 94% accuracy through 400 hand-labeled examples.

Can I replicate your research?

Yes. Every article links to a public GitHub repository containing all data and code needed to reproduce the analysis. Our main replication repository contains 18 research projects with complete documentation.