brycewang-stanford/Auto-Empirical-Research-Skills / skills/09-meleantonio-awesome-econ-ai-stuff/_skills/analysis/python-panel-data
python-panel-data
UnverifiedPanel data analysis with Python using linearmodels and pandas.
Python Panel Data
Purpose
This skill helps economists run panel data models in Python using pandas, statsmodels, and linearmodels, with correct fixed effects, clustering, and diagnostics.
When to Use
- Estimating fixed effects or random effects models
- Running difference-in-differences on panel data
- Creating regression tables and plots in Python
Instructions
Follow these steps to complete the task:
Step 1: Understand the Context
Before generating any code, ask the user:
- What is the unit of observation and panel identifiers?
- Which outcomes and regressors are required?
- What fixed effects or time effects are needed?
- How should standard errors be clustered?
Step 2: Generate the Output
Based on the context, generate Python code that:
- Loads and cleans the data with
pandas - Sets a MultiIndex for panel structure
- Fits the model using
linearmodels.PanelOLSorRandomEffects - Outputs results in a readable table and optional LaTeX
Step 3: Verify and Explain
After generating output:
- Interpret key coefficients
- Note assumptions (strict exogeneity, parallel trends, etc.)
- Suggest robustness checks (alternative clustering, placebo tests)
Example Prompts
- "Run a two-way fixed effects model with firm and year effects"
- "Estimate a DiD using state and year fixed effects"
- "Export panel regression results to LaTeX"
Example Output
# ============================================
# Panel Data Analysis in Python
# ============================================
import pandas as pd
from linearmodels.panel import PanelOLS
# Load data
df = pd.read_csv("panel_data.csv")
# Set panel index
df = df.set_index(["firm_id", "year"])
# Create treatment indicator
df["treat_post"] = df["treated"] * df["post"]
# Two-way fixed effects model
model = PanelOLS.from_formula(
"outcome ~ 1 + treat_post + EntityEffects + TimeEffects",
data=df
)
results = model.fit(cov_type="clustered", cluster_entity=True)
print(results.summary)
Requirements
Software
- Python 3.10+
Packages
pandaslinearmodelsstatsmodels
Install with:
pip install pandas linearmodels statsmodels
Best Practices
- Always verify panel identifiers and balanced vs unbalanced panels
- Cluster standard errors at the appropriate level
- Check for missing data before estimation
Common Pitfalls
- Failing to set a proper panel index
- Using pooled OLS when fixed effects are required
- Misinterpreting coefficients without accounting for fixed effects
References
- linearmodels documentation
- statsmodels documentation
- Wooldridge (2010) Econometric Analysis of Cross Section and Panel Data
Changelog
v1.0.0
- Initial release
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| Agent Cost Reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 117k | Updated | Claude CodeCodex | Unverified | Install |
| Agent Cost Reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 117k | Updated | Claude CodeCodex | Unverified | Install |