Univariate Time Series Analysis

This lecture covers the analysis of univariate time series, focusing on concepts such as stationarity, ARMA processes, lag operators, invertibility, unit roots, and Dickey-Fuller tests. The instructor addresses the challenges of model selection, estimation, and diagnostics in ARMA modeling, emphasizing the Box-Jenkins approach. Practical examples illustrate the application of autocorrelation and partial autocorrelation functions in determining the appropriate lag structure for AR and MA terms. The lecture concludes with insights on the estimation of ARMA models using methods like OLS and maximum likelihood, along with the importance of unit root tests in time series analysis.