Time Series Class - Part 1 - Dr Ioannis Papastathopoulos, University of Edinburgh

Dive into the fundamentals of time series analysis in this comprehensive lecture from the University of Edinburgh. Explore key concepts including moving average, autoregressive, and ARMA models. Learn about parameter estimation, likelihood-based inference, and forecasting techniques. Advance to more complex topics such as state-space models, hidden Markov models, and the Kalman filter. Discover applications of these concepts and gain insights into recurrent neural network models. Cover essential elements like continuous time series, white noise, random walk, autocorrelation estimation, and statistical tests for stationarity. Understand how to remove trends and work with causal processes in time series data.

Introduction
Motivation
Continuous Time Series
Key ingredients
Time series
Traditional approach
White noise
Random walk
Estimating autocorrelation
Partial autocorrelation
Inferential properties
Statistical tests
Stationarity tests
Removing trends
Causal processes