[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
RE: Re: st: Detecting Outliers
Along the line of Nick Cox's suggestion and Ronan's advice - you could generate BMI (body mass index) variable that would unify height and weight followed by a histogram. These ought to identify the extremes.
> From: firstname.lastname@example.org
> Subject: Re: st: Detecting Outliers
> Date: Wed, 3 May 2006 15:31:14 +0100
> To: email@example.com
> On 2 Beal 2006, at 14:27, Raphael Fraser wrote:
> > my objective is simple to locate potential outliers then cross check
> > with patient records to ensure that the information is legitimate.
> > error free.
> You will have to look at multivariate outliers, then. A height of
> 160cm is believable as is a weight of 120 Kg, but in combination they
> suggest error (but do not prove it). You need to think of groups of
> measures which, together, define outliers.
> Ronán Conroy
> +353 (0) 1 402 2431
> +353 (0) 87 799 97 95
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
Join the next generation of Hotmail and you could win the adventure of a lifetime
* For searches and help try: