Rapid estimates and nowcasting | |
Course Leader | Pim OUWEHAND |
Target Group | Staff of national statistical institutes involved in the production process who want to acquire a good understanding of nowcasting methods and practices |
Entry Qualifications | - Sound command of English. Participants should be able to make short interventions and to actively participate in discussions
- Basic knowledge of time series analysis and statistics
- Basic knowledge of programming language R
|
Objective(s) | - To provide the participants with a state of the art knowledge of the methodology and practice of nowcasting
- To introduce the participants to the use of R to produce nowcasts for their own series.
|
Contents | - Overview of nowcasting: purpose, difference with forecasting, flash estimates, coincident and leading indicators, mixed frequency data, practical examples
- Brief review of time series analysis, including main concepts as trend cycle, seasonal, and regression components and related time-series issues such as stationarity, overfitting, outlier detection and cointegration
- Nowcasting process: data related issues, model selection, auxiliary data selection, cross validation, quality measures, trade-off between timeliness and accuracy,
- Nowcasting methods: naïve, Exponential Smoothing, (S)ARIMA(X)-models, bridge models, structural time series models, dynamic factor models, multivariate analysis, combining forecasts techniques
- Practical exercises using R
|
Expected Outcome | Participants are expected to become familiar with the main methodologies used Nowcasting, understanding their potential and their limitations. After attending the course, they should also be able to implement those methods and cope with the issues that may arise in the practice of nowcasting, such as quality issues and data related issues. |
Training Methods | - Presentations and lectures, practical examples
- Exchange of views/experiences on national practices
- Exercises
|
Required Reading | None |
Suggested Reading | - Hyndman,R.J., Athanasopulos, G., Forecasting, Principles and Practice, Chapter 8, https://otexts.com/fpp2/arima.html
- Commandeur, J.F. and S.J. Koopman (2007), An introduction to state space time series analysis, Oxford University Press
- Eurostat and United Nations (2017), Handbook on rapid estimates
|
Required Preparation | Participants should supply a brief document with information about their education, position, organisation and expectations of the course (max 200 words) |
Trainer(s)/
Lecturer(s) | Pim OUWEHAND (Statistics Netherlands) Bob LODDER (Statistics Netherlands) Frank P. PIJPERS (Statistics Netherlands) |