Summary of Modeling Cycles: MA, AR, and ARMA Models (FRM Part 1 – Book 2 – Chapter 13)

00:00:00 - 00:20:00

This video covers the topics of modeling cycles, autoregressive models, and ARMA models. The author explains how these models can be used to predict future prices and behavior. He also shows how the Yule Walker equation can be used to estimate the parameters of an AR model.

• 00:00:00 This video covers the models MA, AR, and ARMA models. Moving averages are used to model time series, and auto regression is used to predict future performance. The two models are combined to create an ARMA process autoregressive moving average model.
• 00:05:00 This video explains how modeling cycles works, with MA, AR, and ARMA models. The moving average process can be used for financial risk management and economic applications, such as predicting future prices. If the theta term is less than one absolute value, the moving average process is considered an autoregressive infinite process.
• 00:10:00 This video covers the concepts of modeling cycles, autoregressive models, and AR models. The autoregressive model AR one is an auto regressive process that uses only information from the past to predict the future.
• 00:15:00 The author discusses how, when estimating the auto regressive parameters, an AR model is needed instead of an ordinary least-squares model. The Yule Walker equation is used to estimate theta. The process is covariance stationary and will behave similarly to the ar1 process. If the moving average and auto regressive models are combined, a better approximation of the world representation is obtained.
• 00:20:00 In this video, the author explains how seasonal fluctuations can be modeled using automatic correlation and moving average models. He then shows how volatility can be modeled using the same principles.