Can I use this for time series forecasting?

Absolutely. It includes comprehensive tools for ARIMA, SARIMAX, VAR, and exponential smoothing, along with stationarity tests like ADF and forecast confidence intervals.

Does this skill support R-style formulas?

Yes, the skill fully supports the statsmodels.formula.api, allowing you to define models using the 'y ~ x1 + x2' syntax familiar to R users, including automatic dummy variable coding.

When should I use Statsmodels instead of Scikit-learn?

Use Statsmodels when you need rigorous statistical inference, p-values, and diagnostic tests. Scikit-learn is optimized for predictive performance, while Statsmodels is designed for understanding relationships and testing hypotheses.

What diagnostic tests are included for regression validation?

It provides a wide array of tests including Breusch-Pagan for heteroskedasticity, Ljung-Box for autocorrelation, Jarque-Bera for normality, and influence statistics like Cook's distance.

Statsmodels Statistics & Econometrics

Name: Statsmodels Statistics & Econometrics
Author: Weiwei-Mao

byWeiwei-Mao

Ciencia de Datos y ML

Implements rigorous statistical modeling, econometrics, and time series analysis using Python's statsmodels library.

Acerca de

Statsmodels is a specialized Claude Code skill designed for data scientists and researchers requiring formal statistical estimation and inference. It provides a comprehensive suite of tools for fitting linear regression models, generalized linear models, discrete choice models, and complex time series analysis. This skill excels at providing detailed diagnostics, residual analysis, and publication-quality summary tables, making it the preferred choice for econometrics and academic-grade statistical testing where coefficient significance and model assumptions are paramount.

Características Principales

Comprehensive linear modeling including OLS, WLS, and GLS with robust standard errors.
Advanced time series analysis including ARIMA, SARIMAX, and VAR forecasting.
Extensive diagnostic testing for heteroskedasticity, autocorrelation, and normality.
Generalized Linear Models (GLM) for Poisson, Binomial, and Gamma distributions.
0 GitHub stars
Support for R-style formula API for intuitive model specification.

Casos de Uso

Conducting econometric research with rigorous coefficient inference and diagnostic testing.
Validating regression model assumptions through residual analysis and outlier detection.
Forecasting future values in time-ordered datasets using SARIMAX or Exponential Smoothing.

Acerca de

Características Principales

Comprehensive linear modeling including OLS, WLS, and GLS with robust standard errors.
Advanced time series analysis including ARIMA, SARIMAX, and VAR forecasting.
Extensive diagnostic testing for heteroskedasticity, autocorrelation, and normality.
Generalized Linear Models (GLM) for Poisson, Binomial, and Gamma distributions.
0 GitHub stars
Support for R-style formula API for intuitive model specification.

Casos de Uso

Conducting econometric research with rigorous coefficient inference and diagnostic testing.
Validating regression model assumptions through residual analysis and outlier detection.
Forecasting future values in time-ordered datasets using SARIMAX or Exponential Smoothing.