Topics in Finance
Full Time// 3rd Semester, Course Code: ΜΕΧΡΗ314
Part Time // 3rd Semester, Course Code: ΜΕΧΡΗ-Μ314
Credits: 6
Learning Outcomes
The aim of the course is to develop a framework for studying the important question of predictability in financial markets. We will develop econometric tools that can be used to detect and evaluate predictive ability. In addition, addressing the question from an economic point of view, we will examine the value of predictability to investors in real time. While the focus will mostly be on time-series predictability, we will also discuss some examples of cross-sectional predictability.
Upon successful completion of the course, students should be able to:
- use real financial asset return data to rigorously test for the forecasting ability of given variables.
- understand and appreciate the difference between in-sample and out-of-sample predictability.
- evaluate the economic value of real-time trading strategies built on predictive models.
- critically approach the question of financial markets predictability, from both a statistical and an economic viewpoint.
General Competences
- Search for, analysis and synthesis of data and information, with the use of the necessary technology
- Decision-making
- Working independently
- Team work
- Production of new research ideas
Course Content
- Introduction to prediction. The crystal ball utopia.
- Predictive regressions for asset returns. Review of the linear regression model with stochastic regressors. Adjusted R-square as measure of significance. Robust standard errors in the presence of heteroscedasticity and serial correlation.
- In-sample versus out-of-sample statistical significance. Out-of-sample R-square. Mean squared prediction error.
- The economic significance of return predictability. Portfolio choice for mean-variance investors. Small R-square can generate significant excess returns and gains in Sharpe ratios. The role of risk aversion. Predictability and market efficiency.
- Popular predictors at monthly or lower frequency (dividend yield, term spread, default yield spread, etc.)
- Variance risk premium: a daily predictor for S&P 500 returns.
- Cross-sectional predictability: some simple momentum strategies based on broad stock and bond indexes.
Student Performance Evaluation
Assessment will be based on (a) empirical analysis homework assignments (50%) and (b) a final project (50%). Homework will be assigned every 3 weeks on average during the semester. For the homework assignments and the project students will be asked to analyze real data, use Excel, or an equivalent spreadsheet program, and write simple code in R, Matlab, or an equivalent programming language. Students can discuss the assignment questions with each other, but everyone must submit individual assignments.
Bibliography
Suggested Bibliography
- Presentation slides.
Additional bibliography:
- “Α Comprehensive Look at the Empirical Performance of Equity Premium Prediction” by Ivo Welch and Amit Goyal, The Review of Financial Studies, Vol. 21, Issue 24, July 2008, pp. 1455-1508.
- “Predicting Excess Stock Returns Out of Sample – Can Anything Beat the Historical Average?” by John Campbell and Samuel Thompson, The Review of Financial Studies, Vol. 21, Issue 24, July 2008, pp. 1509-1531.
- “The Dog That Did Not Bark: A Defense of Return Predictability” by John Cochrane, The Review of Financial Studies, Volume 21, Issue 4, July 2008, Pages 1533–1575.
- “Risk Premia Harvesting Through Dual Momentum” by Gary Antonacci, Social Science Research Network, 2017.
- “Risk Premia Harvesting Through Dual Momentum” by Gary Antonacci, Social Science Research Network, 2017.
Related Academic Journals
Master of Science (M.Sc.) in
«Banking and Finance»
Specialization in
«Banking and Financial Management»