Skip to main content
2 events
when toggle format what by license comment
Jul 22, 2020 at 16:27 comment added Alexis "If you can assume that any neighborhood in the city are not really different from one another" You cannot: neighborhood-level research is precisely interested in explaining between-neighborhood differences in my experience. Assuming homogeneity is not reality here. I get the resource/data efficiency/statistical power trade off in cluster sampling... I do not buy the homogeneity argument at all—an argument which seriously breaks down since a single cluster's estimate should represent whole pop reducto ad absurdum (and it is at odds with what I have seen in the applied literature).
Jul 22, 2020 at 5:58 history answered Nuclear241 CC BY-SA 4.0