Articles • EventStudy

Methods

Conceptual explanations of return models, test statistics, and advanced designs — with formulas, assumptions, and references.

Methods Gate: Smoke Test
Methods: Return Models
Methods: Test Statistics
Methods: Panel / Difference-in-Differences
Methods: Intraday Event Studies
Methods: Synthetic Control
Methods: AI Advisor
Methods: Diagnostics & Robustness

Get Started

Package overview with a complete Dieselgate worked example.

Introducing EventStudy: A Powerful Tool for Event Study Analysis in R

Gallery

Browse all vignettes by topic.

Gallery

Core Workflow

From raw price data to publication-ready results — extraction, diagnostics, and robust inference.

Result Extraction and Export
Diagnostics and Validation for Event Studies
Inference and Robustness: HAC, Bootstrap, and Multiple Testing

Return Models

Multi-factor, time-varying, GARCH, BHAR, volume, volatility, and custom return models.

Factor Models, GARCH, and Buy-and-Hold Abnormal Returns
Time-Varying Beta Models: Rolling Window and DCC-GARCH
Creating Custom Models
Volume and Volatility Event Studies

Test Statistics

Parametric and non-parametric test statistics, and how to create your own.

Creating Custom Test Statistics

Advanced Designs

Panel DiD with modern estimators, intraday event windows, and synthetic control.

Panel Event Studies: A Guide Following Miller (2023)
Modern Difference-in-Differences Estimators
Intraday Event Studies with EventStudy
Synthetic Control Methods

Cross-Sectional & Simulation

CAR-level regression on firm characteristics and Monte Carlo power analysis.

Cross-Sectional Analysis of Event Study Results
Monte Carlo Simulation and Power Analysis

AI Advisor

Grounded AI advisor — two-layer walkthrough with the bundled Dieselgate dataset.

The Grounded AI Advisor: A Dieselgate Multi-Automaker Walkthrough

Data & Reporting

Downloading market and factor data, and automated RMarkdown report generation.

Downloading Stock and Factor Data
Automated Event Study Reports

Worked Examples

Complete end-to-end analyses across distinct financial domains – from raw data through model fit, test statistics, plots, and interpretation.

Example: Earnings Surprise Analysis (AAPL, MSFT, GOOGL)
Example: Regulatory Shock -- Dieselgate VW-Group vs Peers
Example: M&A Deal Announcements -- Power Analysis on Synthetic Data