[DDI-CDG] Re: [DDI-SRG] Longitudinal data proposal

[I-Lin Kuo]

Hi Sanda,

I have a question:

"It will also be necessary to identify, for each variable, the
respondent, analysis unit, universe, and certainly the physical data
file containing the variable. "

What's "the respondent"? I'm confused because the other things
mentioned, "analysis unit", etc., are "variable-wide", so to speak,
but my understanding of "the respondent" is that it pertains only to a
single record, so wouldn't be a comparison criteria.