Statistics for Finance
This module develops the statistical foundations required for rigorous empirical work in finance. While the tools are general, every concept is framed around financial applications — from testing the normality of returns to diagnosing regression models used in factor analysis.
Module Overview¶
Week | Topic | Applications |
|---|---|---|
1–2 | Distributions and Inference | Return distributions, hypothesis tests, p-values |
3–4 | Regression and Diagnostics | Factor models, OLS, heteroskedasticity |
5–6 | Maximum Likelihood Estimation | GARCH estimation, distribution fitting |
7 | Bootstrap Methods | Confidence intervals for Sharpe ratios |
Philosophy¶
Statistics in finance is not just about computation — it’s about understanding what the numbers mean and where they can mislead. We pay particular attention to:
The assumptions behind each test and what happens when they’re violated
The difference between statistical significance and economic significance
Common pitfalls: data snooping, look-ahead bias, overfitting
“All models are wrong, but some are useful.” — George Box