I'm working with Gretl and I'm trying to introduce 'boost (impulso) variable' as a dependent variable in my ARIMA model but I'm not sure about the inputs that Arima function needs. 
I'm transforming my series by adding regular and seasonal differences. I have only a model with a constant but I see in residual plot against time an 'outlier' in t0. What input Gretl need to estimate w0 'boost (impulso) variable' coeficient? Could be an all-zero vector except for a 1 in t = t0 (called I)? Or could be sd_d_I?
Thanks a lot!

Sigue los principales acontecimientos deportivos en directo. MSN Motor