P.Mean: Processing skip fields in SPSS (created 2008-09-25).

How do I program skips on SPSS so that data would not be entered on irrelevant questions?

For those of you who have not encountered skips, this is a technique in a survey where you ask a question and if they answer one way, you would ask some additional questions about the same topic, but if they answered the question a different way, all of those questions would be irrelevant. For example, you might ask how many hours a day someone watches television, and then follow-up with questions about particular shows or stations. If they do not have a television in their home (a rare person, indeed, but there are a few of them out there), any further questions along these lines are irrelevant. For these people, a comment on the margins of the survey asks them to skip to the next page or something similar.

In such a survey, you would create a special code (99, for example) for anyone who skipped questions. Be sure to think carefully about how you want to analyze this data. When you are measuring the proportion of people who watch a specific television show, is it a proportion out of all people or a proportion out of all people who have a television.

In general, skip patterns will cause confusion and lead to poor quality of responses. Some people who should skip will fail to do so and other will skip when they shouldn't. Some will skip to the wrong page. So you should only use skip patterns if you absolutely have to, and then only in a limited amount. Consistency in the skip patterns will help. For example, when someone skips, they always skip to the top of the next page, or they always skip to the very last page.

Surveys done on a computer or on a website would allow you to process skip patterns easily, so consider this if you haven't already sent out your survey.

Data entry with skip patterns is tedious and error prone, so I would encourage extra data checking. As far as I know there are not any programs in SPSS that will process skip patterns in a survey, though the company does have a special module SPSS data entry that may have this capability.

A really bright programmer would be able to write a program to process skip patterns, but if you were a smart programmer, you wouldn't be reading web pages from a hack like me, would you? Seriously, though, the amount of effort in developing a program to process skip patterns is considerable, and may only make sense if you have thousands of surveys to process.

Creative Commons License This work is licensed under a Creative Commons Attribution 3.0 United States License. This page was written by Steve Simon and was last modified on 2010-04-01. Need more information? I have a page with general help resources. You can also browse for pages similar to this one at Category: Survey design.