Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st:normal linear (mis)scaling


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st:normal linear (mis)scaling
Date   Thu, 5 Aug 2004 15:57:27 +0100

. help mathfun 

indicates some functions with bounded range. 
Then use some linear re-expression to suit. 

2 * invlogit(x) - 1 

maps to (-1,1). Now tell me that it _really_ 
has to be [-1,1] not (-1,1).... 

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

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu]On Behalf Of 
> D.Christodoulou
> Sent: 05 August 2004 14:23
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st:normal linear (mis)scaling
> 
> 
> Nick,
> 
> thanks for your reply. In the same sense I can use:
> - histogram normal if normal >= -0.2 | normal <=-0.8 -
> to remove the exact bit that I want.
> 
> However, it is essential for this distribution to have bounds in the
> interval [-1,1].
> How to I restrict the random observations to be generated into this
> interval.
> 
> thanks again,
> Dimitris
> 
> Nick Cox wrote:
> > 
> > I would generate lots of values from a Gaussian
> > and then take a big bite out of it, with some
> > randomness about the biting.
> > 
> > . set obs 1000
> > . gen normal = invnorm(uniform())
> > . qnorm normal
> > . histogram normal if (abs(normal) * uniform()) > 0.5
> > . histogram normal if (abs(normal) * uniform()) > 0.6
> > 
> > Nick
> > n.j.cox@durham.ac.uk
> > 
> > D.Christodoulou
> > >

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index