We are particularly concerned about spurious correlation arising from the (semanticscholar.org)
Even if someone did tests using Granger - causality, I'd still be suspicious of the result, whichever way it would point, because of the high probability of finding spurious correlations. (alephblog.com)
This had it's genesis in a «comment» on my 2009 paper on spurious correlations in work by McKitrick and Michaels and separately, de Laat and Maurelis. (realclimate.org)