Derrick P. Reagle

Forecasting Financial Crises in Emerging Market Economies

This article identifies six fundamental indicators that might predict a financial crisis similar to the one that affected the emerging markets of Southeast Asia. Our empirical analysis shows that the 1997 Asian crisis could have been predicted. Probit estimation reveals that a small number of common indicators can forecast a financial crisis well. The estimation gives estimates that are robust to either cross-section or panel data. We suggest an aggregate indicator that combines all the individual indicators and calculates the optimal thresholds for the indicators. This aggregate indicator has similar predictive properties and reduces the calculations to determine the probability of crisis.

Preparing for the worst : incorporating downside risk in stock market investments

List of Figures.List of Tables.Preface.1. Quantitative Measures of the Stock Market.1.1. Pricing Future Cash Flows.1.2. The Expected Return.1.3. Volatility.1.4. Modeling of Stock Price Diffusion.1.5. Efficient Market Hypothesis.Appendix: Simple Regression Analysis.2. A Short Review of the Theory of Risk Measurement.2.1. Quantiles and Value at Risk.2.2. CAPM Beta, Sharpe, and Treynor Performance Measures.2.3. When You Assume ...2.4. Extensions of the CAPM.Appendix: Estimating the Distribution from the Pearson Family of Distributions.3. Hedging to Avoid Market Risk.3.1. Derivative Securities: Futures, Options.3.2. Valuing Derivative Securities.3.3. Option Pricing Under Jump Diffusion.3.4. Implied Volatility and the Greeks.Appendix: Drift and Diffusion.4. Monkey Wrench in the Works: When the Theory Fails.4.1. Bubbles, Reversion, and Patterns.4.2. Modeling Volatility or Variance Explicitly.4.3. Testing for Normality.4.4. Alternative Distributions.5. Downside Risk.5.1. VaR and Downside Risk.5.2. Lower Partial Moments (Standard Deviation, Beta, Sharpe, and Treynor).5.3. Implied Volatility and Other Measures of Downside Risk.6. Portfolio Valuation and Utility Theory.6.1. Utility Theory.6.2. Nonexpected Utility Theory.6.3. Incorporating Utility Theory into Risk Measurement and Stochastic Dominance.6.4. Incorporating Utility Theory into Option Valuation.6.5. Forecasting Returns Using Nonlinear Structures and Neural Networks.7. Incorporating Downside Risk.7.1. Investor Reactions.7.2. Patterns of Downside Risk.7.3. Downside Risk in Stock Valuations and Worldwide Investing.7.4. Downside Risk Arising from Fraud, Corruption, and International Contagion.8. Mathematical Techniques.8.1. Matrix Algebra.8.2. Matrix-Based Derivation of the Efficient Portfolio.8.3. Principal Components Analysis, Factor Analysis, and Singular Value Decomposition.8.4. Itos Lemma.8.5. Creation of Risk-Free Nonrandom g(S, t) as a Hedge Portfolio.8.6. Derivation of Black-Scholes Partial Differential Equation.8.7. Risk-Neutral Case.9. Computational Issues.9.1. Sampling, Compounding, and Other Data Issues in Finance.9.2. Numerical Procedures.9.3. Simulations and Bootstrapping.Appendix A: Regression Specification, Estimation, and Software Issues.Appendix B: Maximum Likelihood Estimation Issues.Appendix C: Maximum Entropy (ME) Bootstrap for State-Dependent Time Series of Returns.10. What Does It All Mean?Glossary of Greek Symbols.Glossary of Notations.Glossary of Abbreviations.References.Name Index.Index.

Experience Weighted Attraction in the First Price Auction and Becker Degroot Marschak

In this paper we explore the performance of Experience Weighted Attraction (EWA) in two different auction institutions: First Price Sealed Bid, and Becker-DeGroot-Marschak. Our results suggest that learning has some promise as a possible explanation for previously documented cross- institutional choice anomalies usually attributed to risk aversion. Additionally, we present results on the likely econometric (ir)recoverability of EWA parameters in these institutions.

Inference for negativist theory using numerically computed rejection regions

A negativist theory is a theory that asserts that an affect is absent. Negativist theories are common in statistics and require a test procedure to avoid biasing the conclusions in favor of accepting the theory. New critical value tables are provided and computational methods are introduced to ease practical difficulties with the resulting non-contiguous interval null. Simulations compare the power function of negativist testing to traditional hypothesis testing. A case study, using Canadian stock market data, does not always support efficient markets (an example of a negativist theory) and reverses previous studies using positivist hypothesis tests.