Time Series Analysis
The course is taught to PhD & Masters students and considers the use of modern time series methods. Topics covered largely focus on the application of multivariate methods. These include the use of autoregressive distributed lag models, vector autoregression models, structural vector autoregression models, SVAR identification by short-run restrictions, SVAR identification by long-run restrictions, Bayesian vector autoregression models, SVAR identification by sign restrictions, SVAR analysis in a data-rich environment, cointegration and error-correction, regime-switching VAR and SVAR models, multivariate volatility models and nowcasting models. Throughout the course we will emphasize areas of ongoing research.
This particular page is work in progress so many of the links may not work.
Course outline [link]
1) Autoregressive distributed lag models [slides] [tutorial] [R files]
2) Vector autoregressive models [slides] [tutorial] [R files]
3) Structural vector autoregressive models [slides] [tutorial] [R files]
4) SVAR identification by short-run restrictions [slides] [tutorial] [R files]
5) SVAR identification by long-run restrictions [slides] [tutorial] [R files]
6) Bayesian vector autoregressive models [slides] [tutorial] [R files]
7) SVAR identification by sign restrictions [slides] [tutorial] [R files]
8) SVAR identification by alternative methods [slides] [tutorial] [R files]
9) SVAR analysis in a data-rich environment [slides] [tutorial] [R files]
10) Cointegration and error correction models [slides] [tutorial] [R files]
11) Nonlinear regime-switching models [slides] [tutorial] [R files]
12) Multivariate volatility models [slides] [tutorial] [R files]
13) Nowcasting models [slides] [tutorial] [R files]