Forecasting Methods

Objectives

  • To obtain an understanding of common statistical methods used in business and economic forecasting;
  • To develop the computer skills required to forecast business and economic time series data;
  • To gain insights into the problems of implementing and operating large scale forecasting systems for use in business.

General characterization

Code

100086

Credits

6.0

Responsible teacher

Carolina Maria de Abreu Braziel Shaul

Hours

Weekly - Available soon

Total - Available soon

Teaching language

Portuguese. If there are Erasmus students, classes will be taught in English

Prerequisites

Matrix algebra and statistics (recommend)

Bibliography

Shumway, R.H. and Stoffer, D.S. Time Series Analysis and its Application with R Examples, 3rd edition, Springer, 2011. (http://www.stat.pitt.edu/stoffer/tsa3/); Makridakis, S., Wheelwright, S.C., Hyndman, R.J. Forecasting: Methods and Applications, 3rd edition, John Wiley & Sons, 1998.; Forecasting: principles and practice: https://www.otexts.org/book/fpp; Little Book of R for Time Series: http://a-little-book-of-r-for-time-series.readthedocs.org/en/latest/; Murteira, B., Muller, D., Turkman F. Análise de Sucessões Cronológicas, 1ª edição, McGraw Hill, 1993

Teaching method

Theoretical and pratical classes. On the theoretical class students will learn the main concepts of forecasting methods. On practical classes students will solve exercises and practical cases on the concepts addressed in the theoretical class.

Evaluation method

Two options:

  • Continuous assessment (Three multiple choice mid-term tests (50%) and One assignment (50%))
  • Second exam period (100%)

There is no first exam period!

Subject matter

  1. Introduction to forecasting and R
  2. Time series graphics
  3. Time series decomposition
  4. The forecaster's toolbox
  5. Time Series Regression
  6. Exponential smoothing 
  7. ARIMA models
  8. Dynamic regression 
  9. Advanced forecasting methods