This is the merge request that follows the previous one (!110 (merged)).
@rfernand, @jcos and I have just modified the function so that both the one-sided and two-sided are performed following Steiger (1980). The dependence between the forecast and the reference forecast is taken into account with this methodology. Also, the autocorrelation of the time series is also taken into account by computing the effective number of degrees of freedom with s2dv::Eno (this was already included in the previous version).
We are going to test the new version of the function with our scripts to ensure that it works correctly.
@acarreri, in case you also want to do some tests.