EViews.com

I must admit that I don't entirely understand what you are trying to do with your calculation. The following shows the equivalence between post-multiplying the data by the eigenvectors and the score series created using normalize loadings scaling. Note that as expected the average sum of the squared...

In the language of factors, multiple terms in @expand gives the interaction effects, but not the main effects.

How about a built-in

100 * @ranks(x) / @obs(x)

Is there a chance you can share your workfile. In all of my test cases I'm not seeing this discrepancy. (Note that the model simulation doesn't include the coefficient uncertainty, but in my cases, I'm not seeing much difference from that).

Question, you can always create an undated workfile with that kind of labeling. Is there anything that you need date wise that isn't handled by an undated with custom labels?

It is an interesting idea and I can understand the appeal There are, however, legal issues that make this not quite as simple a request as one might think. Given this fact and the existence of third-party encryption tools which can be used to encrypt a workfile, this feature is currently not high on...

We are looking into this for you. It may take a bit but we will let you know what we discover.

You want the comparison to the mean of the other variables for each observation?

Can you be a bit more specific about what you are doing? What values in AA need to be copied? Is it the value for one date, or values for a range of dates? Are we matching up observations by-date?

Forecast of data at t+4 given information at t.

You can request the forecast standard errors and construct intervals from those.

If you are okay with a separate regression line for both the non-2008/2009 values and for the the 2008/2009 values, the easiest way to do this is to create new series that have missing data for subsections of the data. That is, create a series with just the 2008 and 2009 values, and a separate serie...

Take a look at the by-stats functions:

http://www.eviews.com/help/helpintro.ht ... stics.html

We've identified the issue. In the MacKinnon algorithm for the response surface, we have found that there are potential issues with the polynomial approximation to the response surface for extreme values. In this case, the statistic value is so out of bounds that the existing algorithm approximation...