[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: hadimvo: multivariate outlier detection
Dear List members,
Could anyone tell me what the interpretation of the hadi-distance is?
The Stata manual (see hadimvo) states that it is "the distance (not the
distances squared) from the basic subset", but I do not understand
this. Perhaps because I expected that I could interpret these distances
as z-values, but playing around a bit with some data created using the
-corr2data sbp age sex com1, n(1000) m(120 50 .4 .2) sd(12
7 .048989 .04)-
-hadimvo sbp age sex com1, gen(odd distance)-
showed distances varying between 0.227 and 4.429, and not values
roughly between -3 and 3.
Any help will be greatly appreciated.
Gerben ter Riet, MD PhD, Academic Medical Center
Dept. General Practice, Room J3-354, 1105 AZ Amsterdam
* For searches and help try: