Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Variable names and labels for interaction terms


From   "Nic" <[email protected]>
To   <[email protected]>
Subject   st: Variable names and labels for interaction terms
Date   Tue, 22 Mar 2011 21:23:12 -0400

Hello all,

I've figured out how to create all my (continuous x continuous) interaction variables at once but I'm trying to learn how to (1) automatically create variable labels for them, and (2) name the new variables based on truncated versions of the component variables' names.

Here is what I have so far:

foreach x of varlist s* {
foreach y of varlist f* {
generate i`x'_x_`y' =`x'*`y'
}
}

(1) I'd like each interaction term's variable label to be comprised of the component variables' labels. For example, a label that reads, "Physical Abuse x Self-Esteem". I'm guessing this is possible since I can apply a single original variable label using the tips found here:
http://www.stata.com/support/faqs/data/variables.html
But I'm having trouble figuring out how to do something similar in the more complex scenario when two variables are involved. Any hints?

(2) I'd also like the interaction term variable names to be based on truncated versions of the component variables' names. For example, "is1f1" would be an ideal name for an interaction term created from "s1PhysicalAbuse" and "f1SelfEsteem". Currently my code creates variable names that are quite lengthy, for example, "is1PhysicalAbuse_x_f1SelfEsteem". It would save a lot of typing in later analyses if I were able to refer to a particular interaction by typing just the prefixes for the predictor and moderator variables. Again, any hints?

With thanks,
Nic
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index