add sampling weights to resample_data?

[graemeblair]

add sampling weights to resample_data?

[aaronrudkin]

In the single level case this is fairly simple (just take a vector of length N); it ends up being a little more complicated in the multiple level balanced case, and very complicated in the multiple level stochastic case. It may be a failure of my imagination, but I'd like someone who had a clear use case for this to explain to me what kind of weight data we might think users would provide in the complex cases before I think about laying down a UI that enables it.

[nfultz]

For above complicated hypotheticals, can't you can already do that with randomizr and elbow grease? It should be fewer than three lines of code.

…

On Wed, Mar 7, 2018 at 10:08 AM, Aaron Rudkin ***@***.***> wrote: In the single level case this is fairly simple (just take a vector of length N); it ends up being a little more complicated in the multiple level balanced case, and very complicated in the multiple level stochastic case. It may be a failure of my imagination, but I'd like someone who had a clear use case for this to explain to me what kind of weight data we might think users would provide in the complex cases before I think about laying down a UI that enables it. — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#96 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AAZjTob1-u5b-f7oTIW6SLUaALwWD4NTks5tcCILgaJpZM4SgwqY> .