This comprehensive webinar is hosted through Zoom and runs over a total of 9 hours, with 4 hours each day (2 in the morning and 2 in the afternoon) with an extra Q&A session on the second day.
The aim of this course is to provide participants with an in-depth understanding of the fundamental concepts of time series modelling and forecasting and with the practical skills to use STATA to model and forecast economic time series.
Model and forecast from a univariate AR(FI)MA or multivariate VAR model. Model and forecast from a univariate GARCH (including EGARCH, TARCH, APARCH and GJR moels)or a multivariate GARCH model ( including the CCC,DCC, VEC models). Distinguish between stationary and nonstationary series and understand the implications of using nonstationary series; Build, estimate and forecast from univariate and multivariate time series models using Stata. Understand and critically evaluate recent research in time series
Two days of online instruction for four hours per day.
Two hours each morning, followed by two hours each afternoon.
Hour-long Q&A session at the end of each day to address queries.
Session 1: Getting started with time series data: visualization and testing. Unit roots tests, types of non –stationarity. Assessing the memory of economic and financial data over time: the auto covariance and autocorrelation functions. Pure time series models of the mean: AR, MA, ARMA, ARFIMA models: introduction, dependence structure and the Box Jenkins methodology to choose the best model.
Session 2: Estimation of AR(I)(FI)MA models in Stata . Post estimation diagnostic tests: is the model good enough? How to improve it. Forecasting with ARMA models. Adding exogenous variables to ARMA models: the ARDL framework.
Session 1: Pure time series models of the variance: the GARCH models. GARCH, EGARCH, TARCH, APARCH: estimation and post diagnostic tests in Stata. Do we really need a GARCH? The ARCH test. The ARMA-GARCH framework.
Session 2: Capturing multivariate time dependences: the VAR and MGARCH models: estimation, testing, post diagnostic tests in Stata. Which model is best for your research? Examples of successful research papers on time series analysis in Stata.
The number of delegates is restricted. Please register early to guarantee your place.