This course
will focus on methods in time series econometrics designed to handle “big
data.” We will talk about univariate predictive regressions with many
regressors, discussing various dense and sparse regularization techniques, such
as principal components, ridge, lasso and others. We will discuss Bayesian inference in the
context of these regressions and explore the connection between Bayesian
shrinkage and regularization. The course will then cover some of the most
popular multivariate econometric models for big data. We will talk about
dynamic factor models, looking at different estimation techniques, including
Bayesian. The course will also cover Bayesian VARs, detailing in particular how
they can be used to deal with mixed-frequency and irregularly sampled data. We
will discuss applications of these models and methods to nowcasting and
forecasting in macroeconomics and finance. We will also touch on machine
learning for macroeconomic forecasting.
- Professor: Monti Francesca