The judge declined to invalidate the soda rule based on those precedents, since a key prong of the analysis is whether the rule required expertise to be drafted.
But Scott Zeger, the head of the department of biostatistics at Johns Hopkins, who performed the statistical analysis in the study, points out that clustered sampling is the rule rather than the exception in public-health studies, and that the patterns of deaths caused by epidemics are also very variable by location.
The other Dark Social though is the fallibility of sentiment analysis and the question we have to ask is whether the 20% rule is at all appropriate now that people communicate in small bits of text rather than in blogs.