Discussion Paper

No. 2017-5 | February 08, 2017
Are linear models really unuseful to describe business cycle data?

Abstract

The authors use first differenced logged quarterly series for the GDP of 29 countries and the euro area to assess the need to use nonlinear models to describe business cycle dynamic behaviour. Their approach is model (estimation)-free, based on testing only. The authors aim to maximize power to detect non-linearities and, simultaneously, they purport avoiding the pitfalls of data mining. The evidence the authors find does not support some descriptions because the presence of significant non-linearities is observed for 2/3 of the countries only. Linear models cannot be simply dismissed as they are frequently useful. Contrarily to common knowledge, nonlinear business cycle variation does not seem to be a universal, undisputable and clearly dominant stylized fact. This finding is particularly surprising for the U.S. case. Some support for nonlinear dynamics for some further countries is obtained indirectly, through unit root tests, but this can hardly be invoked to support nonlinearity in classical business cycles.

Data Set

  • almru.xlsx
    [application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, 72K]

JEL Classification:

C22, C51, E32

Assessment

  • Downloads: 426

Links

Cite As

Artur Silva Lopes and Gabriel Florin Zsurkis (2017). Are linear models really unuseful to describe business cycle data? Economics Discussion Papers, No 2017-5, Kiel Institute for the World Economy. http://www.economics-ejournal.org/economics/discussionpapers/2017-5


Comments and Questions


Anonymous - Referee Report 1
February 13, 2017 - 08:18

see attached file


Artur Silva Lopes and Gabriel Florin Zsurkis - Reply to referee report
February 27, 2017 - 11:41

see attached file


Marc Paolella - Reader Comment
February 14, 2017 - 09:03

see attached file


Artur Silva Lopes and Gabriel Florin Zsurkis - Reply to Marc Paolella
February 27, 2017 - 11:42

see attached file