Analyzing two paired variables
If you ask the same question twice to the same respondent, or a similar question with the same options, the two variables are considered 'paired'. This is often used in a pre-, post test design, but also on surveys if you ask for example two questions on the same scale, about a similar topic.
With two nominal variables we could be interested to see if people changed their mind, with two ordinal if there is a difference, and also with two scale variables. With the unpaired versions it was more often about relation than about differences.
Click on the left to go to a specific type of paired data that you have to learn how to analyze it.