spb/tools-spboucher-ai

1{2  "slug": "linearmodels",3  "name": "linearmodels",4  "aliases": [],5  "vendor": { "name": "Kevin Sheppard", "slug": "kevin-sheppard", "website": "https://bashtage.github.io/linearmodels/" },6  "homepage_url": "https://bashtage.github.io/linearmodels/",7  "docs_url": "https://bashtage.github.io/linearmodels/",8  "repo_url": "https://github.com/bashtage/linearmodels",9  "license_url": "https://github.com/bashtage/linearmodels/blob/main/LICENSE.md",10  "product_type": "library",11  "product_status": "active",12  "summary": "Python package by Kevin Sheppard adding panel data, instrumental-variable, system (SUR/3SLS) and asset-pricing estimators missing from statsmodels",13  "description": "linearmodels is a Python library by Kevin Sheppard that fills the gaps in statsmodels for applied econometrics and empirical finance. Its panel module offers pooled OLS, fixed effects (PanelOLS with entity, time and other effects), random effects, between, first-difference and Fama-MacBeth estimators plus AbsorbingLS for high-dimensional effects; the IV module provides 2SLS, LIML, GMM, continuously updated GMM and JIVE with weak-identification and specification tests; system estimation covers SUR, 3SLS and system GMM; and the asset-pricing module implements two-step and GMM linear factor models and a SUR model for traded factors. Clustered, heteroskedasticity-robust and kernel covariance estimators are available throughout, with formula interfaces and pandas MultiIndex panels as inputs.\n\nThe package is released under the University of Illinois/NCSA license, follows statsmodels conventions and prints comparable summary tables. Version 7.1 is current at the time of writing. It is single-machine and does not cover nonlinear panel models or dynamic panel GMM (Arellano-Bond), for which R or Stata remain more complete.",14  "capabilities": ["Panel estimators: pooled, fixed, random, between, first-difference, Fama-MacBeth", "AbsorbingLS for high-dimensional fixed effects", "IV: 2SLS, LIML, GMM, CUE-GMM, JIVE with diagnostics", "System estimation: SUR, 3SLS, system GMM", "Linear factor asset-pricing models", "Clustered and robust covariance estimators", "Formula interface and pandas MultiIndex panels"],15  "workflows": ["Two-way fixed-effects panel regression with clustered errors", "Fama-MacBeth cross-sectional asset-pricing tests", "IV estimation with weak-instrument diagnostics"],16  "advantages": ["Covers estimators statsmodels lacks", "Consistent with pandas and statsmodels conventions", "Permissive NCSA licence"],17  "limitations": ["No dynamic panel GMM (Arellano-Bond)", "Linear models only", "Smaller community than statsmodels"],18  "prerequisites": ["Python with NumPy, pandas and statsmodels"],19  "audiences": ["Empirical finance researchers", "Applied econometricians working in Python"],20  "alternatives": ["statsmodels", "fixest", "arch", "stata"],21  "comparison_notes": "statsmodels covers general regression and time series but not panel IV or system models; fixest in R is faster for many-level fixed effects and includes event-study tooling; arch, by the same author, addresses volatility and bootstrap methods.",22  "categories": [{ "slug": "econometrics-causal-inference", "primary": true }, { "slug": "hf-finance-research" }],23  "tags": ["python", "econometrics", "panel-data", "open-source"],24  "use_cases": ["estimate-causal-effects", "write-papers"],25  "operating_systems": ["macos", "linux", "windows"],26  "execution_modes": ["local"],27  "interfaces": ["library"],28  "deployment_models": ["embedded"],29  "integrations": ["pandas", "NumPy", "statsmodels", "formulaic"],30  "data_formats": ["pandas DataFrame (MultiIndex)", "NumPy arrays", "xarray"],31  "languages": ["Python", "Cython"],32  "source_model": "open-source",33  "license_spdx": "NCSA",34  "pricing_model": ["free", "open-source"],35  "self_hostable": true,36  "sources": [37    { "url": "https://bashtage.github.io/linearmodels/", "type": "official_site", "title": "linearmodels 7.1", "supports": ["name", "summary", "capabilities", "vendor"], "checked_at": "2026-11-02" },38    { "url": "https://github.com/bashtage/linearmodels", "type": "repository", "title": "bashtage/linearmodels", "supports": ["repo_url"], "checked_at": "2026-11-02" },39    { "url": "https://github.com/bashtage/linearmodels/blob/main/LICENSE.md", "type": "license_page", "title": "linearmodels LICENSE.md", "supports": ["license_spdx", "source_model"], "checked_at": "2026-11-02", "note": "University of Illinois/NCSA Open Source License text" }40  ],41  "confidence": "high",42  "discovery_method": "editorial-research",43  "depth": "standard",44  "editorial_status": "reviewed",45  "visibility": "public",46  "featured": false,47  "author": "batch-E"48}49