Sven, 

thanks a lot. The ternary operator - beautiful. 

To the questions ... I do have four dataset (variance, volatility, logVariance, logVolatility) each with approx 100 series, so I do not want to merge them into one dataset. The idea is to have four sessions, into each session I load the specific dataset and then run a script that estimates a lot of models on the current dataset and produces models/fitted values into the current session. Like this, I get to have all the variables/models/fits/etc in each separate session. For this purpose, I want to have one script instead of four, that is the gist of the idea. 

The simplest piece of code that reproduces the error I get is the following snippet:

open anscombe.gdt

strings xNames = array(2)

        xNames[1] = "x"

        xNames[2] = "y1"

list xVariables = @xNames[1] @xNames[2]

Thank you!

Daniel