FORECAST OUT-OF-SAMPLE ....HELP!!!

[FASTONE]

HEY PEOPLE
I NEED SOME HELP WITH THIS TOPIC

I RECENTLY DOING A WORKFILE WITH TIME SERIES AND A SMALL SAMPLE 2001 2011
MACRO VARIABLES, ANNUAL DATA
ALL OK (HETER.., AUTOCORR, RAMSEY TEST, ETC.) THEN WAS TO THE FORECASTING

FIRST, I ADJUST THE SAMPLE IN THE WORKFILE (PROC STRUCTURE/RESIZE...) 2001 2015
THEN I WENT TO THE FORECASTING AND ADJUST THE FORECAST SAMPLE 2001 2015
BUT THE OUTPUT WINDOW ONLY DISPLAY GRAPH UNTIL 2011 (ADJUSTED SAMPLE)
THEN I RUN THE FORECASTING AGAIN BUT ONLY FOR 2012 2015
AND PROMPT THE MESSAGE: "UNABLE TO COMPUTE DUE TO MISSING VALUES"
THE BOX FOR "INSERT THE ACTUALS FOR OUT-OF-SAMPLE OBSERVATIONS" WAS CHECKED PRVIOUSLY
SO WHAT HAPPEND??? !!!

THE MANUAL SAY THAT:
Insert actuals for out-of-sample observations.
By default, EViews will fill the forecast
series with the values of the actual dependent variable for observations not in the
forecast sample. This feature is convenient if you wish to show the divergence of the
forecast from the actual values; for observations prior to the beginning of the forecast
sample, the two series will contain the same values, then they will diverge as the forecast
differs from the actuals. In some contexts, however, you may wish to have forecasted
values only for the observations in the forecast sample. If you uncheck this
option, EViews will fill the out-of-sample observations with missing values.

IF I FILL WITH THE LAST OBSERVATION FOR EVERY INDEPENDET VARIABLE
THE FORECAST VALUES WILL BE THE SAME TO THE LAST VALUE OF THE DEPENDENT VARIABLE OBSERVED.

HELP ME
PLEASE!!!!!

[EViews Gareth]

Do you have values for your independent variables for the forecast period?

[elturco]

I am sorry I do not have a reply for this question. But I am wondering for something else. When you forecast, the program creates a graph with forecast values and +/- SE values as shown in the chart above. Then program creates a new series in workfile for those forecast values. However the program does not create series for +/- SE values so where can I find the series for the +/- SE values instead of just seeing them in line graph? Thx

[EViews Gareth]

When you hit the forecast button you can optionally choose to save the forecast standard errors in the workfile.

[elturco]

Attached is the forecast window and I do not see that option of choosing SE's to be in work sheet.

[EViews Gareth]

Its the box that is labelled "S.E. (optional)".

[elturco]

awesome. Thank you.

[FASTONE]

Do you have values for your independent variables for the forecast period?

That`s is my question. If i dont have any observation for the period of forecast -out of sample- then i can´t do the forecast?
My sample for example is: 2000-2011. With that i run the models etc. Then i want to forecast 2012-2014 for example but i dont have that observations because they are in the future. I can't do the forecast??? if the answer is yes, then for what work this?? i want to predict the future, not verify theoreticaly my data sample.
Could explain me some og this because now i am confusse.
Thank you!

[EViews Gareth]

If you say that Y depends upon X, then to predict Y you need a value for X. Simple maths.

[FASTONE]

If you say that Y depends upon X, then to predict Y you need a value for X. Simple maths.

There is a way of automatically generate regressors to predict is achieved. Or the only predictions that can be made are short term ones

[EViews Gareth]

No, EViews has no way to magically generate values for regressors. You have to define a model for them too.