Jump to content

Talk:Structural break

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia

Dr. Pitarakis's comment on this article

[edit]

Dr. Pitarakis has reviewed this Wikipedia page, and provided us with the following comments to improve its quality:


There is a sizeable literature on changepoints dating back to the 50s that has been ignored.

More rigour is needed when defining what a break is (breaks in mean, variance, regression parameters etc).

Statements such as "breaks can lead to huge forecasting errors" are not very helpful or even meaningful. There are certainly other concerns related to the presence or absence of breaks that would be worthwhile discussing.

The technical description is really very limited and not informative at all.


We hope Wikipedians on this talk page can take advantage of these comments and improve the quality of the article accordingly.

We believe Dr. Pitarakis has expertise on the topic of this article, since he has published relevant scholarly research:


  • Reference 1: Pitarakis, Jean-Yves, 2011. "Joint Detection of Structural Change and Nonstationarity in Autoregressions," MPRA Paper 29189, University Library of Munich, Germany.
  • Reference 2: Jean-Yves Pitarakis, 2003. "Least Squares Estimation and Tests of Breaks in Mean and Variance under Misspecification," Econometrics 0312004, EconWPA.

ExpertIdeasBot (talk) 19:50, 1 July 2016 (UTC)[reply]

Dr. Calmes's comment on this article

[edit]

Dr. Calmes has reviewed this Wikipedia page, and provided us with the following comments to improve its quality:


Rather brief for such a topic, but generally correct. Examples could be given, like when the way data are collected change, generating a structural break.

Oil shocks (supply shocks ) provide an excellent illustration too. Given the challenges of stationarity tests, reference to oïl shocks is particularly relevant (cf. Perron).

Note that institutional changes such as regulatory amendments, trade agreements etc. can also lead to structural breaks.


We hope Wikipedians on this talk page can take advantage of these comments and improve the quality of the article accordingly.

We believe Dr. Calmes has expertise on the topic of this article, since he has published relevant scholarly research:


  • Reference : Christian Calmes & Raymond Theoret, 2013. "The change in banks' product mix, diversification and performance: An application of multivariate GARCH to Canadian data," RePAd Working Paper Series UQO-DSA-wp012013, Departement des sciences administratives, UQO.

ExpertIdeasBot (talk) 14:27, 7 July 2016 (UTC)[reply]

Dr. Guidolin's comment on this article

[edit]

Dr. Guidolin has reviewed this Wikipedia page, and provided us with the following comments to improve its quality:


A. A structural break appears when we see an unexpected shift in a (macroeconomic) time series.

COMMENT: Structural breaks certainly affect all kind of time series; in fact they can affect random variables that are not ordered in time, i.e., not only time series.

B. Other challenges are where there are:

COMMENT: I think here we need a WHEN THERE ARE, or IN CASE THERE ARE.

C. There are several programs that can be used to find structural breaks, including R and GAUSS.

COMMENT: without references or links, this blank claim should be removed.

D. If there are too many unknown breaks, then just assume the parameter to be time varying.

COMMENT: I would re-phrase as

"In case too many breaks are inferred from the data, which makes locating them awkward, it is often best to simply assume a time-varying parameter process."

I would generally erase the "More sophisticated model" section. Or after the first sentence replace with

"A Survey of further techniques of detection and estimation is:

Eksi, O. (2009). Structural break estimation: A survey. Unpublished working paper. Universitat Pompeu Fabra, Barcelona, Spain."


We hope Wikipedians on this talk page can take advantage of these comments and improve the quality of the article accordingly.

We believe Dr. Guidolin has expertise on the topic of this article, since he has published relevant scholarly research:


  • Reference : Daniele Bianchi & Massimo Guidolin & Francesco Ravazzolo, 2013. "Macroeconomic factors strike back: A Bayesian change-point model of time-varying risk exposures and premia in the U.S. cross-section," Working Paper 2013/19, Norges Bank.

ExpertIdeasBot (talk) 18:50, 26 July 2016 (UTC)[reply]

Dr. Hendry's comment on this article

[edit]

Dr. Hendry has reviewed this Wikipedia page, and provided us with the following comments to improve its quality:


https://drive.google.com/file/d/0B8-wWhGFpGYCYXJZaURXc0R1MHc/view?usp=sharing


We hope Wikipedians on this talk page can take advantage of these comments and improve the quality of the article accordingly.

We believe Dr. Hendry has expertise on the topic of this article, since he has published relevant scholarly research:


  • Reference : Jennifer L. Castle & Jurgen A. Doornik & David F. Hendry & Ragnar Nymoen, 2012. "Mis-specification Testing: Non-Invariance of Expectations Models of Inflation," Working Paper Series 50_12, The Rimini Centre for Economic Analysis.

ExpertIdeasBot (talk) 02:37, 6 September 2016 (UTC)[reply]