James P. (Pat) Johnson (jpjohn@ix.netcom.com) wrote: : I am writing a syntax file to score a questionnaire which has 240 : items (Q1 to Q240). The items are scored 1 for true and 2 for false. . . . <snip> : I want to preserve the original responses by the subjects because I : have to recode for reversals and then recode to do sums. I can do : that on the original items, and it works fine, but I'd like to also : keep the original responses by the subjects intact.

RECODE X1 to Xn (.....) INTO Y1 to Yn

is a way to get a new set of variables, if you really need them.

You can skip using the "INTO", and your original responses will remain intact, if you save your new file by a new name. When you do a GET FILE, you can change the names if you want, matching the files with the two versions of the items. But: Do you really need to save the modified items at all, by ANY name? Rather than looking at 240 items, aren't you doing your analyses on Totals, or just specially selected items?

Rich Ulrich, biostatistician wpilib+@pitt.edu Western Psychiatric Inst. and Clinic Univ. of Pittsburgh