Thread by @olson_km

#JSM2018 Peter Miller appearing as a Northwestern University emeritus professor, providing comments on the CNSTAT reports

#JSM2018 Miller Survey paradigm vs multiple data source paradigm. Surveys may become irrelevant b/c they are slow, not granular, not nimble, costly, not sustainable

#JSM2018 Miller Multiple Data sources require new: methods, computing resources, privacy protections, training, data quality frameworks. Not cheap. What does this give us?

#JSM2018 Miller Report focuses on trade offs - trade off between precision and timeliness and granularity. But this isn’t a new thought - the idea that we aren’t fast enough or at low levels pervades reports

#JSM2018 Miller Will a multiple data source approach give us something new? Report reads like a tool in search of a purpose - where is the dialogue between policy makers and what the information needs might be?

#JSM2018 Miller Report is pessimistic about surveys, but talks about how surveys are an important part of multiple data sources. Report doesn’t talk about how new changes in survey research now or how to sustain surveys for commingling

#JSM2018 Miller Adaptive survey design requires thinking new ways about surveys, data quality. Allow us to have stopping rules, flow processing to do editing, weighting during data collection. Need transparency in protocols for these new approaches.

#JSM2018 Miller Survey approaches discussed in report doesn’t have to be one we actually use

#JSM2018 Miller gives an Arthur C Clarke quote. Warns that transparency is key to avoid the new methods from seeming like “magic” (we don’t want magic data)