Financial Econometrics I

Lecture Notes for the MaFE

Preface

These notes accompany the Financial Econometrics module of the MaFE.

Structure of this course

The module runs over twelve teaching weeks, preceded by a preparatory week, Week 0. Each week below links to its own chapter.

Delivery schedule for C1: Financial Econometrics

Week	Date (Year 1)	Format
Week 0	4 Jan 2027	C1 preparation, online
Week 1	11 Jan 2027	Live online lectures
Week 2	18 Jan 2027	Online learning
Week 3	25 Jan 2027	Online learning
Week 4	1 Feb 2027	Small class discussion, online
Week 5	8 Feb 2027	Online learning
Week 6	15 Feb 2027	Group discussion, online
Week 7	22 Feb 2027	Live online lectures
Week 8	1 Mar 2027	Online learning
Week 9	8 Mar 2027	Online learning
Week 10	15 Mar 2027	Small class discussion, online
Week 11	22 Mar 2027	Online learning
Week 12	29 Mar 2027	Group discussion, online

How each lesson is built

Every lesson follows the same rhythm:

1. Learning objectives — what you will be able to do afterwards.
2. The problem — a practical question that motivates the method.
3. The method — the econometrics, with the minimum algebra that is honest.
4. In Python — the implementation, line by line.
5. Reading the output — how a professional interprets the result.
6. What can go wrong — assumptions, diagnostics, and common misuse.
7. Key takeaways and Exercises.

Software

All code is in Python. From the project folder:

python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
python scripts/fetch_data.py

scripts/fetch_data.py is the only code in the project that touches the network. It downloads daily prices from Yahoo Finance and the factor files from Kenneth French’s data library, and caches them as Parquet in data/. Lessons read from that cache, so the notes render offline and the numbers never change underneath you.

Every lesson opens with the same preamble:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import fe1tools as fe

fe.setup()

Notation

Notation used throughout

Symbol	Meaning
\(P_t\)	Price of an asset at the end of period \(t\)
\(R_t\)	Simple return, \(P_t/P_{t-1} - 1\)
\(r_t\)	Log return, \(\ln(P_t/P_{t-1})\)
\(R_t^f\)	Risk-free rate
\(R_t^e\)	Excess return, \(R_t - R_t^f\)
\(\mu,\ \sigma^2\)	Mean and variance
\(\sigma_t^2\)	Conditional variance at \(t\), given information at \(t-1\)
\(\varepsilon_t\)	Model error / innovation
\(\alpha,\ \beta\)	Regression intercept and slope
\(\hat{\theta}\)	An estimate of the parameter \(\theta\)
\(T,\ N\)	Number of time periods, number of assets

Returns are decimal unless a table says otherwise: 0.012 means 1.2%. Daily figures are annualised with 252 trading days, monthly with 12.

Acknowledgements

The empirical work uses factor data generously made public by Kenneth French, and market data via Yahoo Finance.

Reading List

Textbook	Chapter(s)	Relavant Study Week
Textbook A	Chapter 1,2	Week 1

These notes are a living document. Corrections and suggestions are welcome.