Hi, sorry for this e-mail, but I have not found any other way to find this answer.

I am an economics student from Finland that are using Gretl, and finding it useful tool to analyze data.

We were wondering if Gretl had a function for dividing groups into low and high respondents, in other word we want to test a part of a population (in OLS) who have marked the highest scores in a survey. We want to test this against other answers in the same survey, but are in doubt that Gretl understands that person 1 is the same person when we change the order of respondents by sorting them in the dependent value and then setting the range to half of the population . 

I would really appreciate an answer, thank you.

Best regards

Antti Erkkison