This is probably an easy question, but wanted to confirm before I start doing the analysis for my intro stats course...
So a question I have to answer is as below:
Test the difference between the respondent's cholesterol level and maximum blood pressure. If so, write the difference.
As I understand paired/dependent t-test are for the same subject, however most of the time they are the same measure (ie. before/after). However the two variables I have been given are totally different (continuous) measures... Is this still a paired t-test?
A paired t-test is used when the difference between the two variables is specific to the subject/sample-point. More specifically, we use it when we expect there to be some correlation between the variables that is subject specific. When the two variables are totally independent we use a two sample t-test.
So if your question said something like: ‘Is the average cholesterol level and maximum blood pressure significantly different in this population?’ And if your data from cholesterol level and blood pressure came from two different random samples, then I would say a non-paired test.
However, your question specifically said “the respondents” which tells me you have one sample with two variables. You know both the cholesterol level and blood pressure level for a single respondent. Furthermore, this is health data related to the heart, there is likely a correlation within respondents.