Hi - I recently met with a statistician to discuss some of my data, and learned quite a bit, but was still left with some questions.

I have learned that there is a difference between multivariable and multivariate data; however, I am not certain when to use each approach. I understand that if you have one outcome variable then you would probably use a multivariable, and if you have multiple outcome variables it becomes a multivariate.

My question is - from what kind of data can I use each type of analysis?

Looking at Hidalgo and Goodman (Am J Public Health 2013), they state that "multivariate...refers to the modeling data that are often derived from longitudinal studies, wherein an outcome is measured for the same individual at multiple time points (repeated measures), or the modeling of nested/clustered data..."

Is it unreasonable to perform a multivariate analysis on data that does not conform to one of these two scenarios above? I had previously performed a multivariable analysis (GLM), but I am considering analyzing my data with a multivariate analysis. My data comes from a cohort study of lab values (no repeated tests), and I am wondering which approach is more appropriate for this type of study/data.

Thanks for the help!