Performance and Robustness Characteristics in Statistical Forecasting

Yuriy Kharin
Additional contact information
Yuriy Kharin: Belarusian State University, Department of Mathematical Modeling and Data Analysis

Chapter Chapter 4 in Robustness in Statistical Forecasting, 2013, pp 55-72 from Springer

Abstract: Abstract In this chapter, we define optimality and robustness under distortions for statistical forecasting. The problem of statistical forecasting is stated in the most general form and then specialized for point or interval forecasting and different levels of prior uncertainty. The chapter introduces performance characteristics of forecasting statistics based on loss functions and risk functionals. In order to define mathematically rigorous robustness characteristics, a classification of the types of distortions common to applications is made, and the relevant mathematical distortion models are constructed. Robustness of statistical forecasting techniques is defined in terms of the following robustness characteristics: the guaranteed (upper) risk, the risk instability coefficient, the δ-admissible distortion level.

Keywords: Forecast Error; Innovation Process; Hypothetical Model; Borel Function; Forecast Statistic (search for similar items in EconPapers)
Date: 2013
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-319-00840-0_4

Ordering information: This item can be ordered from
http://www.springer.com/9783319008400

DOI: 10.1007/978-3-319-00840-0_4

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().