In this course, students learn about the theory and methods used when analyzing data that have been collected over time, including autoregressive, moving average, ARMA and ARIMA models, factor tables, filtering and frequency analysis with the spectral density. Students will also learn methods that can handle multiple explanatory variables (multivariate time series), including neural network-based methods such as MLP and RNN. When using these methods and models, students will be able to estimate frequencies in the data and generate forecasts. Students will learn how to apply these methods through lectures, lightboard sessions, coding in R, real-life data sets and interviews with currently practicing industry professionals.
Model Data With Serially Correlated Observations, Autoregressive Models, Moving Average, ARMA and ARIMA Models, Spectral Density and Analysis in the Frequency Domain, Multivariate Time Series Analysis With VAR, Time Series Analysis With Neural Networks (MLP and RNN)