Generate surrogate time series by computing a mean seasonal
trend for each year, and shuffling the residuals. This differs from
make_surrogate_seasonal in that the data are not
sampled uniformly at the same time each year. Thus, we also ask for the
day_of_year as input, in order to compute the mean seasonal trend.
make_surrogate_annual_spline(ts, num_surr = 100, day_of_year = NULL)
| ts | the original time series |
|---|---|
| num_surr | the number of null surrogates to generate |
| day_of_year | a vector of the numerical day of year, e.g. January 1 = 1, January 2 = 2, December 31 = 365 (leap years are a bit funny, but I don't think it should have a large effect) |
A matrix where each column is a separate surrogate with the same
length as ts.