1

Suppose I am differencing a time series. I decide to try out differencing for $d=1, 2$, and $3$ where $d$ is the order of the differencing (by convention of the R function diff()). If $d=2$ illustrates a smaller mean and variance than the other differenced time series, does that imply that $d=2$ does the best job at removing trends?

324
  • 484
  • 2
  • 8

0 Answers0