Skip to content
Econometrics and Financial Time Series / Univariate time series

Overview — Univariate time series

Returns, yields, spreads, and short rates arrive in time order. Their past may help forecast the conditional mean or variance. This topic teaches how to check that claim: fit stationary ARMA models, diagnose unit roots, test equilibrium combinations, and model volatility clustering. A predictive pattern still needs out-of-sample evaluation before it supports a decision.

By the end of this note you should be able to:

  • identify, estimate, and diagnose stationary ARMA models and state Wold, stationarity, and invertibility conditions;
  • distinguish I(0) from I(1), recognise spurious regression, and apply DF/ADF/PP at textbook level;
  • test and model cointegration with Engle–Granger, ECMs, and Johansen as the system extension;
  • test for ARCH effects and estimate GARCH by QMLE with robust inference.

In this lesson

  1. Contents
  2. The big picture

The full lesson is for members.

Read the full lesson

New to SelfMadeQuant.com? See membership options or browse the Econometrics and Financial Time Series syllabus.