In the previous chapter we saw how we could test a hypothesis using a list of numerical values. But how should we proceed if we want to perform a hypothesis test using qualitative values? Qualitative values are usually not numerical, but are often words used as responses to survey questions. Some examples include
Yes/No responses
Political affiliation
Age/income brackets
Gender identity
Marital status
Favorite sport/team/player
School class level
We can’t objectively quantify marital status in order to perform calculations with it, so we need to find an approach that is both objective and valid. One option is to use the proportion (or percentage) of our sample that is represented by one or more of the groups we are surveying. Once we have this numerical value for a qualitative variable, we can perform a hypothesis test on the proportion we are interested in. This chapter will address this approach.