Re: [Gretl-users] How i can calculate the residual in a missing observation in tramo?

TRAMO stands for "Time series Regression with ARIMA noise, Missing values and Outliers". SEATS is "Signal Extraction in ARIMA Time Series". Used as a seasonal adjustment program TRAMO adjusts a series for missing values and outliers. It then passes the adjusted series to SEATS which completes the analysis using the adjusted series. I suspect that you are looking at the SEATS output which gives residuals relative to the output from TRAMO and not the original series. There is a lot of additional material on TRAMO-SEATS at the Bank of Spain web-site http://www.bde.es/bde/en/secciones/servicios/Profesionales/Programas_esta.... You can also download various stand-alone versions of the program. John C Frain 3 Aranleigh Park Rathfarnham Dublin 14 Ireland www.tcd.ie/Economics/staff/frainj/home.html <http://www.tcd.ie/Economics/staff/frainj/home.html> mailto:frainj@tcd.ie <mailto:frainj@tcd.ie> mailto:frainj@gmail.com <mailto:frainj@gmail.com> On 10 June 2016 at 17:50, Manuel Dario Hernandez Bejarano <mdhernandezb(a)unal.edu.co <mailto:mdhernandezb@unal.edu.co>> wrote: Thanks for your answer, I would like to know your opinion when you consider the option "skipping approach", due to the fact that the Kalman filter doesn't assign a residual when you have a missing value, however, in the results, TRAMO gives a value of residual for the point where a missing observation is presented, and I would like to know the reason.