Hello, I'm trying to use an a raima model to forecasting. How to write a script that forecasts forwards some variable? I've dataset/file that includes "X" observations in time and i want to forecast this observation in time hour+1 or hour+2 forewards. How to do it? I know that I should to use "fcast" or "fcasterr" functions, but i don't know how to get time parameters. Please, help me. Best regards, walgula _______________________________________________ Gretl-users mailing list Gretl-users(a)lists.wfu.edu http://lists.wfu.edu/mailman/listinfo/gretl-users

On Wed, 20 Jun 2007, walgula(a)wp.pl wrote: > Hello, I'm trying to use an a raima model to forecasting. How to > write a script that forecasts forwards some variable? I've > dataset/file that includes "X" observations in time and i want > to forecast this observation in time hour+1 or hour+2 forewards. > How to do it? I know that I should to use "fcast" or "fcasterr" > functions, but i don't know how to get time parameters. Example: # open Ramanathan hourly data set open data10-2.gdt # arma (1,1) for electricity usage arima 1 0 1 ; 2 # add 3 observations for out of sample forecast addobs 3 # display out-of-sample forecast fcasterr 32:01 32:03 The "32:01" and "32:03" above are the starting and ending observations for the forecast. If the hourly data were not notated as "day:hour" you might do something like fcasterr 101 103 (assuming the original data went to obs 100, and you want an out-of-sample forecast). Allin Cottrell _______________________________________________ Gretl-users mailing list Gretl-users(a)lists.wfu.edu http://lists.wfu.edu/mailman/listinfo/gretl-users

Hi everyone!, I have the same problem with arima forecasting (SARIMA actually) The problem is that I need to forecast Y for 1, 7, 14 and 28 leads. Meaning that I need for example. But T is dynamic. First I take T=1/10/2006 and want the prediction for 28/10/2006, when I have it, take 2/10/2006 and forecast 29/6/2006 and so on. Is there an easy way to do it in gretl? Thanks Mauricio Giacometti ----- Original Message ----- From: <walgula(a)wp.pl&gt; To: "Gretl list" <gretl-users(a)lists.wfu.edu&gt; Sent: Thursday, June 21, 2007 3:59 AM Subject: Re: [Gretl-users] arima forecasting > Thanks Allin, it works;) > > ----- Original Message ----- > From: "Allin Cottrell" <cottrell(a)wfu.edu&gt; > To: "Gretl list" <gretl-users(a)lists.wfu.edu&gt; > Sent: Thursday, June 21, 2007 3:53 AM > Subject: Re: [Gretl-users] arima forecasting > > >> On Wed, 20 Jun 2007, walgula(a)wp.pl wrote: >> >>> Hello, I'm trying to use an a raima model to forecasting. How to write >>> a >>> script that forecasts forwards some variable? I've dataset/file that >>> includes "X" observations in time and i want to forecast this >>> observation in time hour+1 or hour+2 forewards. How to do it? I know >>> that I should to use "fcast" or "fcasterr" functions, but i don't know >>> how to get time parameters. >> >> Example: >> >> # open Ramanathan hourly data set >> open data10-2.gdt >> # arma (1,1) for electricity usage >> arima 1 0 1 ; 2 >> # add 3 observations for out of sample forecast >> addobs 3 >> # display out-of-sample forecast >> fcasterr 32:01 32:03 >> >> The "32:01" and "32:03" above are the starting and ending observations >> for the forecast. If the hourly data were not notated as "day:hour" you >> might do something like >> >> fcasterr 101 103 >> >> (assuming the original data went to obs 100, and you want an >> out-of-sample forecast). >> >> Allin Cottrell >> >> _______________________________________________ >> Gretl-users mailing list >> Gretl-users(a)lists.wfu.edu >> http://lists.wfu.edu/mailman/listinfo/gretl-users >> > > _______________________________________________ > Gretl-users mailing list > Gretl-users(a)lists.wfu.edu > http://lists.wfu.edu/mailman/listinfo/gretl-users

_______________________________________________ Gretl-users mailing list Gretl-users(a)lists.wfu.edu http://lists.wfu.edu/mailman/listinfo/gretl-users