Re: [Gretl-users] X-12-Arima

On Thu, 9 Sep 2010, John C Frain wrote: Thanks, John, for presenting the expert's view! Although I recently conceded to Henrique's request to trim leading and trailing NAs from the sample passed to X-12-ARIMA, the reason I hadn't done that before was that I had the idea that x12a could handle missing values, if they were given as -9999 (or -99999?). In your previous posting you said, "While the X12-ARIMA manual states that missing values are not allowed there are ways around this. If the missing value is replaced by -99999 then -99999 may be replaced by a value that is regarded as an outlier and then this may be replace by the appropriate Reg-ARIMA fitted value for the purpose of estimation seasonal factors etc. This may require specific X12ARIMA options to be in effect and running X12-ARIMA outside of Gretl." This gives me a general notion, but not enough in the way of specifics to correct my previous (mis-)conception. Do you know of a specific option that can be passed to x12a to get it to interpret -99999 as missing? If so, that could easily be added to gretl's invocation of the program. As regards gretl native code, as you noted we don't accept interior missing values for any dynamic time-series estimators. This is more restrictive than it needs to be: our native Kalman filter can handle NAs, and so our native AR(I)MA (which uses Kalman) should also be able to handle them. But so far this remains on the TODO list (on which there are many other things). Allin