Suppose I have two climate variables that each follow AR(1) (i.e., red noise) statistics and I wish to do a linear regression on them. What is an appropriate number of degrees of freedom to use for statistical calculations? Please give references if you have them.
Use the effective dof instead; ie approx (1-a)/(1 a), where a is the autoregressive coefficient. If my memory serves me, take a look at Nordo 1966. Anyway, ar1 typically underestimates the ac at lags
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment