Macroeconomic Modeling and Forecasting Using R-Studio (INS-CRS)

related image
Deadline for the application has passed.
Course No.: IT 18.05
Location: Washington, D.C., United States
Date: June 12, 2018-June 15, 2018 (4 Days)
Language: English

Target Audience:

Officials, primarily in ministries of finance, economy, and planning, or in central banks.


It is required that candidates have an advanced degree in economics, strong analytical skills, and a very good knowledge of English. Courses will be conducted in English with no interpretation.

Course Description:

In the current data rich environment, macroeconomic modeling and forecasting become more important and challenging. This course focuses on econometric and statistical methods and theory useful for modeling and forecasting dynamically dependent data. It will also discuss some recent developments in statistical analysis of high-dimensional time series. The course emphasizes application and empirical data analysis using R-Studio. Professor Tsay will start with data visualization for multivariate dependent data and a brief introduction to R-Studio. Then, he will introduce multivariate time series analysis, especially the vector autoregressive models, vector autoregressive models with exogenous variables, and regression models with time series errors. He will consider model selection, model simplification, parameter constraints, model checking, and forecasting. The course then discusses unit-root non-stationarity, co-integration, and error-correction models. For high-dimensional data, it will consider various factor models, diffusion index, principal component regression, and partial least squares. Professor Tsay will also discuss the LASSO-type models for dependent data and mixed-frequency data forecasting. Finally, he will consider model averaging, random forest, and deep learning for forecasting in a data-rich environment.

The goals of the course are:

•  to gain experience in modeling and forecasting macroeconomic time series via R-Studio;
•  to understand the dynamic dependence and features of macroeconomic data;
•  to learn recent developments in econometric and statistical analysis of high-dimensional time series including penalized regression, random forest, and deep learning; and
•  to study the usefulness of using high-frequency data to improve and revise forecasting.

Data analysis is an integral part of the course and real examples will be used throughout the lectures and lab exercises. The course will use various R packages in data analysis, but no prior knowledge of those packages is required. All packages and commands will be given in the lecture.

Target Audience:  This is an intermediate to advanced level course. Participants should have taken an introductory sequence in econometrics at the graduate level.

Important Note for Online Courses:

For Online Learning (OL) courses, which are delivered through the edX platform, you will need an additional piece of information to register: you will be prompted for your edX.org username. If you do not already have a username, please go to https://courses.edx.org/register and sign up for a free account. Once you have created an account, you may complete the IMF Institute application. If you already have an edX account, your username can be found on the top right of the screen after logging in.

Important Note for Internal Economics Training Courses:

Internal Economics Training (IT) courses are self-financed. The IMF will not charge officials for attending courses. However, all travel, insurance, hotel, and living costs will need to be covered by the agency sponsoring the participants.