quant-statistics

Analyze financial time-series with ADF, cointegration, Granger causality, and GARCH models.

Updated Aug 27, 2026

Search Tags:#time-series #bootstrap #garch #cointegration #granger-causality #regression-diagnostics #adf-test

Ready to run

npx skills add https://github.com/prinzeval/Vibe-Trading --skill quant-statistics-prinzeval

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: quant-statistics
Source: https://github.com/prinzeval/Vibe-Trading/tree/main/VALENDATA/agent/src/skills/quant-statistics
Command: npx skills add https://github.com/prinzeval/Vibe-Trading --skill quant-statistics-prinzeval

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provide a comprehensive suite of quantitative statistical methods for analyzing financial time-series, enabling robust testing, volatility modeling, and diagnostic evaluation essential for strategy research and risk management.

Core Features & Use Cases

ADF Unit-Root Test for stationarity assessment of time-series data.
Cointegration tests to identify long-run relationships useful for pair trading.
Granger causality tests to explore predictive relationships between series.
GARCH family volatility modeling (GARCH(1,1) and variants) for volatility forecasting.
Regression diagnostics including heteroskedasticity, autocorrelation, and multicollinearity checks.
Bootstrap and hypothesis-testing frameworks to assess significance under non-normal financial data.

Quick Start

Provide your time-series data and run the available functions to test stationarity, estimate volatility, and perform diagnostic checks

Frequently Asked Questions about quant-statistics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I test time-series stationarity and cointegration for pairs trading?▼

You can test time-series stationarity using the ADF unit-root test, and identify long-run pairs trading relationships by running cointegration tests on multiple asset price series.

What is the best way to model and forecast volatility for financial assets?▼

The best way to model and forecast volatility for financial assets is using GARCH family variants, such as GARCH(1,1), which estimate conditional variance to predict future volatility across equities, foreign exchange, and cryptocurrencies.

Can I use regression diagnostics to check heteroskedasticity and autocorrelation in my data?▼

Yes, you can run regression diagnostics to check for heteroskedasticity, autocorrelation, and multicollinearity in your quantitative research data to ensure the validity of your statistical inferences and model parameters.

How does Granger causality testing work for predicting time-series relationships?▼

Granger causality testing evaluates whether past values of one time-series statistically predict another series, helping quantify predictive relationships for strategy development.

When should I use bootstrap methods for hypothesis testing on financial data?▼

You should use bootstrap methods for hypothesis testing on financial data when dealing with non-normal distributions, allowing you to accurately assess significance without relying on strict parametric assumptions.