Granger Causality Testing in High-Dimensional VARs: A Post-Double-Selection Procedure
(2023) In Journal of Financial Econometrics 21(3). p.915-958- Abstract
- We develop an LM test for Granger causality in high-dimensional (HD) vector autoregressive (VAR) models based on penalized least squares estimations. To obtain a test retaining the appropriate size after the variable selection done by the lasso, we propose a post-double-selection procedure to partial out effects of nuisance variables and establish its uniform asymptotic validity. We conduct an extensive set of Monte-Carlo simulations that show our tests perform well under different data generating processes, even without sparsity. We apply our testing procedure to find networks of volatility spillovers and we find evidence that causal relationships become clearer in HD compared to standard low-dimensional VARs.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/0da33691-5009-4804-a068-ece29123e6e6
- author
- Hecq, Alain ; Margaritella, Luca LU and Smeekes, Stephan
- organization
- publishing date
- 2023
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Granger causality, high-dimensional inference, post-double-selection, vector autoregressive models, C55, C12, C32
- in
- Journal of Financial Econometrics
- volume
- 21
- issue
- 3
- pages
- 44 pages
- publisher
- Oxford University Press
- external identifiers
-
- scopus:85163332791
- ISSN
- 1479-8417
- DOI
- 10.1093/jjfinec/nbab023
- language
- English
- LU publication?
- yes
- id
- 0da33691-5009-4804-a068-ece29123e6e6
- date added to LUP
- 2021-11-04 13:42:29
- date last changed
- 2023-10-26 14:59:40
@article{0da33691-5009-4804-a068-ece29123e6e6, abstract = {{We develop an LM test for Granger causality in high-dimensional (HD) vector autoregressive (VAR) models based on penalized least squares estimations. To obtain a test retaining the appropriate size after the variable selection done by the lasso, we propose a post-double-selection procedure to partial out effects of nuisance variables and establish its uniform asymptotic validity. We conduct an extensive set of Monte-Carlo simulations that show our tests perform well under different data generating processes, even without sparsity. We apply our testing procedure to find networks of volatility spillovers and we find evidence that causal relationships become clearer in HD compared to standard low-dimensional VARs.}}, author = {{Hecq, Alain and Margaritella, Luca and Smeekes, Stephan}}, issn = {{1479-8417}}, keywords = {{Granger causality; high-dimensional inference; post-double-selection; vector autoregressive models; C55; C12; C32}}, language = {{eng}}, number = {{3}}, pages = {{915--958}}, publisher = {{Oxford University Press}}, series = {{Journal of Financial Econometrics}}, title = {{Granger Causality Testing in High-Dimensional VARs: A Post-Double-Selection Procedure}}, url = {{http://dx.doi.org/10.1093/jjfinec/nbab023}}, doi = {{10.1093/jjfinec/nbab023}}, volume = {{21}}, year = {{2023}}, }