Risk Econometrics A Practical Guide to Bayesian and Frequentist Methods

Risk Econometrics: A Practical Guide to Bayesian and Frequentist Methods serves as a guide to mastering a growing number of applications in network analysis, environmental science, and healthcare. By avoiding a focus either on time series or cross-sectional/panel data methods and adopting either Frequentist (Classical) or Bayesian approaches, it trains readers to recognize the most important aspects of applied Frequentist and Bayesian statistics, emphasizing methods, insights, and popular advances widely used during the last ten years. Risk Econometrics dives deeply into the assumptions and the pros and cons of statistical methods. Based on R and Python, and accompanied by both exercises and research projects, it reinforces a balance between theory and practice that other books, wedded to only one statistical method, cannot match.

• Combines Frequentist and Bayesian methods in time series, cross sectional, and panel data settings with emphasis in risk modelling using R and Python
• Provides practical guidelines to questions such as knowing when to use various model selection criteria, how to backtest models, and how to spot limitations of various estimation and testing methods
• Includes exercises and applications in new industry projects such as: Risk and return of environmental funds; Systemic risk measures using Bayesian and Frequentist methods; Initial margin setting for Central Clearing Counterparties (CCPs); Measuring overall risk associated with a security relative to the market using MSCI Barra Factor Models

1. Introduction to Risk Econometrics, Data and Software 2. Review of Statistics: Frequentist and Bayesian Methods 3. Financial Returns and Volatility 4. Linear Regression and Factor Models 5. Univariate Time Series Modeling and Forecasting 6. Univariate Volatility Models 7. Multivariate Time Series Modeling and Forecasting 8. Downside Risk 9. Credit Risk 10. Systemic Risk and Financial Stability 11. Climate Risk and ESG Investment 12. High Frequency Data Analysis 13. Sate Space and Regime Switching Models 14. Corporate Financial Policies 15. Big Data and Machine Learning

Upper level undergraduate and masters students, practitioners, and researchers in risk management, business analytics, and climate change science as well as economists and statisticians interested in applied work for various global risks

• Combines Frequentist and Bayesian methods in time series, cross sectional and panel data settings with an emphasis on risk modeling using R and Python
• Includes exercises and applications in new industry projects, such as Risk and return of environmental funds, Systemic risk measures using Bayesian and Frequentist methods, Initial margin setting for Central Clearing Counterparties (CCPs), and Measuring overall risk associated with a security relative to the market using MSCI Barra Factor Models