RE: RE: RE: Only for seasonal?
Permalink
Hmmm... I am not aware of studies that have examined the sensitivity to averaging length for shorter timescales. My intuition is that the averaging length should not change appreciably for shorter timescales because the relevant signal (trend) should be the same at the shorter timescale, it's just that the noise will be larger. Therefore, my best guess is that the 15-year average also would work for intraseasonal (e.g., monthly) timescales.