Lisa D. Cook is worried that the quantity of Big Data cannot compensate for its low quality. Statistics gives us lots of power with representative random samples. Nothing can give us power without the tools to do what representativeness does: Lisa D. Cook: @drlisadcook: "'Without taking data quality into account, population inferences with Big Data are subject to a Big Data Paradox...

...the more the data, the surer we fool ourselves." Well said, Xiao-Li Meng. My talk at NBER AI mtg: poor data quality -> flawed inference -> bias in ML predictions...


#shouldread
#statistics
#riseoftherobots

Comments