My use case is a diary dataset, with 1 to 40 days per participant (~1000). Ideally, I'd want to preserve the amount of group-level variance when synthesizing data, but anonymise the participant identities etc. Don't know if this is possible, and it's still supremely useful without this possibility.
syn.strata doesn't quite fulfill my needs, because I cannot ensure that the data for all participants is well-formed (e.g. some have only constant values or just 1 day), and because it (I think) doesn't cloak strata labels.
I did not quite understand method='nested' but from my tests it doesn't appear to do what I want.
My use case is a diary dataset, with 1 to 40 days per participant (~1000). Ideally, I'd want to preserve the amount of group-level variance when synthesizing data, but anonymise the participant identities etc. Don't know if this is possible, and it's still supremely useful without this possibility.
syn.stratadoesn't quite fulfill my needs, because I cannot ensure that the data for all participants is well-formed (e.g. some have only constant values or just 1 day), and because it (I think) doesn't cloak strata labels.I did not quite understand
method='nested'but from my tests it doesn't appear to do what I want.