RE: st: RE: recoding variables with different min & max into standard scale

[Nick Cox <n.j.cox@durham.ac.uk>]

The book by the Legendre brothers (Legendre binomial?) is a good general source on slightly non-standard [sic] standardisations. 

http://www.bio.umontreal.ca/legendre/numecol.html

All puns should be considered intentional. 

Nick 
n.j.cox@durham.ac.uk 

Daniel Laurison

Thank you, this is exactly what I needed.

On Wed, Feb 2, 2011 at 9:49 AM, Nick Cox <n.j.cox@durham.ac.uk> wrote:

> foreach v of var <varlist> {
>        su `v', meanonly
>        gen new_`v' = (`v' - r(min))/(r(max) - r(min))
> }
>
> There's also a dedicated -egen- function from Stas Kolenikov:
>
> _gstd01 from http://web.missouri.edu/~kolenikovs/stata
>    _gstd01 -- Standardize to [0,1] / / Author: Stas Kolenikov,
>    skolenik@recep.glasnet.ru / This program is an extension to the egen
>    command / that standardize the specified variable into [0,1] range / so
>    that 0 corresponds to the minimum value, and 1, / to the maximum
>
> Nick
> n.j.cox@durham.ac.uk
>
> Daniel Laurison
>
> I have a couple hundred variables all with different ranges, and I
> just need to get them all to be 0-1 (not dummies, but continuous with
> the min value 0 and max value 1 and everything in between keeping its
> original proportions; I'd be just as happy with 0-100 or etc.).  I
> don't need ranks or "standardized" i.e. egen std(var) values.  The
> mathematical formula is simply [var- min(var)]/[max(var)-min(var)] but
> I can't figure out how to make Stata do that; I know I could get the
> ranks, but I want to keep the relative values.  My workaround is to
> egen the constant max & min of each var, and then do a foreach loop
> with the maxvars & minvars for each var in the formula... but there
> has to be a neater, more elegant solution, right?

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/