Distinguishing between homogenous and heterogenous non-causality. Comparing the variances? Average individual Wald statistics (Hurlin test)?
You may be interested in the recently published paper where we examined whether growth preceded or followed data in a panel study of a countries using random effects and distribited lagged models
Stylised fact or situated messiness? The diverse effects of increasing debt on national economic growth
Andrew Bell, Ron Johnston, Kelvyn Jones
Journal of Economic Geography 01/2014; forthcoming. ·
https://www.researchgate.net/publication/256443368_Stylised_fact_or_situated_messiness_The_diverse_effects_of_increasing_debt_on_national_economic_growth?ev=prf_pub
Article Stylised fact or situated messiness? The diverse effects of ...
After several years of research, Hurlin's method seems to be the easiest one:
https://www.univ-orleans.fr/deg/masters/ESA/CH/Causality_20111.pdf
https://www.afse.fr/global/gene/link.php?doc_id=139&fg=1
It can be performed using Wald tests in any econometric software, and the specific Hurlin's test can be computed in Matlab (Octave) / Stata / etc..
- Badges
- Science topic
- Similar topics
- Higher Education
- Universities