Course Syllabus | Financial Time Series Analysis | Quantra Course

Welcome to this video on the course structure of time series analysis. Since time series analysis consists of different models, we have tried to structure them in a simple format. The course is divided into four parts. The first part covers the basic concepts of time series such as returns, linear regression and correlation. You can skip this section if you are aware of them. However, we strongly recommend you to go through them for revision purpose. In part 2, you will move towards the time series forecasting models. These include the autoregression and moving average models. In part 3, you will look at volatility and volatility forecasting models. Finally in part 4, you will work on a capstone project, and also learn about the limitations as well as the future enhancement for time series analysis. In Part 1, initially, you will learn what constitutes time series and what does not. Further, you will learn about different types of returns, including cumulative and log returns. After these concepts, you will go through the four components of the time series. Note that noise will be covered later in the course. Further, you will also learn about linear regression models, which is the foundation for autoregression models.

A major requirement of certain time series models is stationary input. You will understand the basic concept of stationarity. And how to convert non-stationary to stationary input. You will get to know about correlation and its impact on linear regression. Further, the auto correlation function and Partial autocorrelation function plot tells us how data points in a time series are related to the preceding data points. With these concepts under your belt, you will move to the second part of the course. To make sure that your learning is smooth, we will start with simple time series analysis models. You will first look at the autoregression (AR) and moving average (MA) models. You will learn how to construct these forecasting models as well as their limitations. Next, you will move further in the ARMA family of models, namely ARIMA and SARIMA. You can apply your learning in real world as live trading integration is also provided for all strategies. So far, we focused on price data as our variable to predict. Another class of time series models are the volatility forecasting models. These models are covered in part 3 of the course.

You will first understand the concept of volatility and its stylised facts. Further, you will develop the ARCH and GARCH models. These models will help you trade the VIX index of the US markets through VXX ETN. The assets used in the course are specific, but the models can be applied to any market and are thus universal in nature. You will then move to part 4, where you will be able to work on a capstone project. This will help you apply your knowledge. Further, you will look at future enhancements to the models used in the course. A brief on the limitations of time series analysis is also included. Finally, you will wrap with the summary of the concepts and time series models studied in the course. We have provided all the files and codes which can be downloaded for your benefit. An html version of the course structure is provided in the next unit, and can be used as a reference while doing the course..

test attribution text

Add Comment