EViews.com

IS it note possible to program the creation of an Rsquared scalar for an equation? I'd like to have the Rsquareds of a number of equation put into a group but I can't seem to find a command to create a scalar for rsquared similar to the rmse (@rmse(x,y[,s])). Is this rteally not possible?

thanks

Hi, I'm wondering if there's a way to program an equation so that its estimation uses all data up to point of the next forecast. For example, right now I have one part of the sample (sample1) used to estimate the equation and the rest of the sample (sample2) to create the forecast. As here: smpl sam...

Oh I follow. When I put the one month of data in its own series my denominator is 12 instead of 11. Thanks again Gareth, you're the man

Sorry how do you mean? If I have a series and copy one month of data into a new series, the standard deviation should match up with the method you gave me for variance for that month, no?

Thanks!

That seems to have worked. The variance I get isn't exactly the same as when I square the standard deviation in the stats table of a series with just one month of data, not sure why.

I see frequency conversion in the properties for the series but there doesnt seem to be the variance option you mention.

How does the variance come into it though?

Is it possible to program a monthly series from a daily series where the monthly variable is the variance of the daily series?

It worked! thank you again! (I had tried to create a new variable rather than extend the x2)

8

Hi Gareth,

That's essentially what I've been trying but it seems to only create one observation. It creates the observation reight before the start of the newer series and leaves everything else blank.

I am able to make a spliced series of the growth rates of one variable and then the growth rates of the second variable. Now I just need to know how to create a level series using the last data point and "growing" backward.

I understand the logic in reversing it to go backward, but when i tried only one data point was added to the sereis and the rest are still NAs

Thanks. I think that link shows how to extend a series forward using the growth rates of a new series. Please tell me if I'm wrong.

I'm looking to extend a series backward with the growth rates of an old series.

So I have the sample period covering both data sets. For example series 1 is from 1990 to 2000 and series 2 is form 2000 to now. How would I extend series 2 back to 1990 using those growth rates? It's easy in excel but I'm not sure how to do it in eviews. thanks