SigmaField
Start learning

Courses Financial Econometrics

Course 4Coming soon

Financial Econometrics

Modelling real return data: stylised facts, regression, time series, factor models, volatility and GARCH, copulas, and backtesting value-at-risk.

  • 13 modules
  • About 34 hours
  • Before you start: Foundations Levels 3 and 5

Coming soon

Explore the syllabus below, and start with the courses it builds on.

How each module works

  1. 1The market problemWhy practitioners need the model
  2. 2Model and codeThe model, then its implementation
  3. 3Practice setQuick questions with instant feedback
  4. 4Case studyAn industry problem, solved in code
  5. 5Limits and risksWhen the model fails, and what to do

Modules

1.1Stylised factsComing soon
You will learn:
Fat tails, Volatility clustering, Leverage effect, Autocorrelation and the ACF.
Case study:
Explore a decade of index returns
In Python:
ACF of returns and of squared returns
1.2Regression in practiceComing soon
You will learn:
Autocorrelation, Heteroscedasticity, Robust standard errors, Multicollinearity.
Case study:
Newey–West standard errors on a beta
In Python:
statsmodels with HAC errors
1.3Stationary time seriesComing soon
You will learn:
Stationarity, AR, MA, ARMA, Forecasting.
Case study:
Forecasting a rate spread
In Python:
statsmodels tsa tools
1.4Unit roots and cointegrationComing soon
You will learn:
Unit-root tests, Engle–Granger, Error correction, Johansen.
Case study:
A pairs-trading signal
In Python:
statsmodels tsa tools
1.5Factor modelsComing soon
You will learn:
CAPM, Fama–French, Fundamental (Barra-style) models, Tracking error.
Case study:
Build a three-factor model
In Python:
Time-series regressions on factor data
1.6Principal components in practiceComing soon
You will learn:
PCA on yield curves and equities, Factor hedging.
Case study:
Hedge a bond book with three components
In Python:
PCA hedge and residual risk
1.7VolatilityComing soon
You will learn:
Historical volatility, EWMA (RiskMetrics), Realised volatility.
Case study:
EWMA against rolling-window volatility
In Python:
Implement EWMA from scratch
1.8GARCHComing soon
You will learn:
GARCH(1,1) by maximum likelihood, GJR and EGARCH, Volatility term structure.
Case study:
Volatility forecasting
In Python:
Code the likelihood and optimise with SciPy, then compare with the arch package
1.9Multivariate volatility and correlationComing soon
You will learn:
EWMA covariance, Dynamic conditional correlation (DCC), Correlation in a crisis.
Case study:
Correlation breakdown in 2008 and 2020
In Python:
EWMA covariance matrices from scratch
1.10CopulasComing soon
You will learn:
Sklar's theorem, Gaussian and t copulas, Archimedean copulas.
Case study:
Simulate joint tail events
In Python:
Sample from copulas and compare tail dependence
1.11Regime and nonlinear modelsComing soon
You will learn:
Quantile regression, Markov switching, Non-linear and discrete-choice models.
Case study:
Detect market regimes
In Python:
Two-state regime model
1.12Forecast evaluation and VaR backtestingComing soon
You will learn:
Loss functions, Out-of-sample tests, Value-at-risk backtesting.
Case study:
Backtest a value-at-risk model
In Python:
Kupiec and Christoffersen tests
1.13Capstone: your own risk modelComing soon
You will learn:
Data, Model, Estimation, Diagnostics, Backtest.
Case study:
Your own risk model, written up
In Python:
One notebook you could show an interviewer