Financial Literacy for Statisticians
A comprehensive course that translates Wall Street into the language you already speak — statistics, probability, and data science.
Who Is This For?
Every financial concept is mapped to the statistical framework you already know. If you have a background in statistics, data science, or quantitative methods, this course will build your financial literacy without dumbing anything down.
From Datasets to Markets
What financial data looks like, tickers, OHLCV structure, time series anatomy, and data sources (yfinance, FRED).
AvailableReturns, Not Prices
Why we use log returns, stationarity, random walks, unit root tests (ADF), and comparing financial returns to normal distributions.
AvailableFat Tails & Stylized Facts
Heavy tails, excess kurtosis, volatility clustering, autocorrelation of squared returns, QQ plots, and testing for normality.
AvailableCorrelation in Finance
Pearson vs Spearman vs Kendall, rolling correlations, correlation breakdown during crises, and copulas introduction.
AvailableMissing Data & Survivorship Bias
Selection bias in financial datasets, delisted stocks, backfill bias, and how these corrupt statistical analysis.
Risk = Variance (But Not Really)
Variance, semi-variance, Value at Risk, CVaR / Expected Shortfall, downside risk, and why variance alone fails.
AvailablePortfolio Theory is Just Optimization
Markowitz as constrained optimization, efficient frontier, the covariance matrix problem, and shrinkage estimators.
AvailableCAPM & Factor Models = Regression
Beta as regression slope, alpha as intercept, Fama-French as multiple regression, R-squared as explanatory power.
AvailableThe Efficient Market Hypothesis
Random walk tests, serial correlation tests, event studies, and what "no predictability" means statistically.
AvailableInterest Rates & Time Value of Money
Discounting as exponential decay, yield curves as term structure, duration as a derivative, convexity as second derivative.
Stocks & Equity Valuation
DCF as expected present value, P/E ratio as a sufficient statistic, and earnings as a noisy signal.
AvailableBonds & Fixed Income
Yield to maturity as IRR, credit spreads as risk premiums, and duration/convexity as Taylor expansion.
AvailableOptions & Derivatives
Black-Scholes as a PDE solution, Greeks as partial derivatives, implied volatility, and put-call parity.
AvailableCommodities, Gold & Oil
Futures vs spot prices, contango/backwardation, gold as inflation hedge, and ties to predictive models.
Time Series Models for Finance
ARIMA for prices, GARCH for volatility, regime-switching models (HMM), and cointegration for pairs trading.
AvailableMachine Learning in Finance
Feature engineering, walk-forward validation, overfitting landmines, and why most ML papers fail in live trading.
AvailableRisk Management & Stress Testing
Monte Carlo VaR, historical simulation, scenario analysis, extreme value theory (EVT), and tail risk.
AvailableBacktesting & Strategy Evaluation
Sharpe ratio as signal-to-noise, drawdown analysis, multiple testing correction, and p-hacking in finance.
AvailableBehavioral Finance & Market Anomalies
Cognitive biases as systematic errors, momentum and mean-reversion, and how biases create exploitable patterns.
Reading Financial News Statistically
Translating headlines to hypotheses, detecting cherry-picked stats, and understanding market commentary.
AvailableMacroeconomics for Statisticians
GDP, inflation, unemployment as time series, central bank policy as intervention analysis, leading/lagging indicators.
AvailableBuilding Your Own Financial Dashboard
Capstone project: pull live data, compute risk metrics, visualize portfolio performance, and tie everything together.
Companion Python Scripts
Each module includes a standalone Python script with real market data. Download them individually from each module page, or clone the full set from the course repository.
Required packages: pandas, numpy, yfinance, matplotlib, scipy, statsmodels, scikit-learn, arch, seaborn