In order to estimate my model performance on different subgroups (age, sex, race, etc.) I need to have the meta-data for every patient in the dataset.
For the baseline and followup groups, the variables are explained in the variables page (https://sleepdata.org/datasets/chat/variables), and given in the data description files. But for the non-randomized group, I see a few columns without explanations, but I assume that they refer to a few important parameters.
do anyone knows what the columns "ref5", "ref6", "ref8", and "ref9" means? I only know that "ref4" is "race".
Those variables have the same meaning in the non-randomized dataset as they do for the randomized subjects, so you can refer to the meanings in the variables browser. I don't see a ref6 variable anywhere, however.
Hope that helps and thanks for using the site!