Frequencies for first 10,000 rows of region variable in nhamcsopd2009 dataset : geographic | region | Freq. Percent Cum. ------------+----------------------------------- northeast | 3,835 38.35 38.35 midwest | 2,200 22.00 60.35 south | 2,447 24.47 84.82 west | 1,518 15.18 100.00 ------------+----------------------------------- Total | 10,000 100.00 by Jean Roth , jroth@nber.org , 28 Mar 2016