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

st: RE: Transformation


From   "Nick Cox" <[email protected]>
To   <[email protected]>
Subject   st: RE: Transformation
Date   Tue, 21 Oct 2003 10:21:59 +0100

There is no way that this can be normalised, 
as such. Whatever you do, the spike at zero will 
remain a spike of some kind. 

Whether there is a case for treating this 
as a zero-inflated distribution must be unclear
without knowing what the data are, but 
as the non-zeros are not integers, I doubt 
that the most popular solutions apply either. 

Nick 
[email protected] 

> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]]On Behalf Of fyzzz
> 
> I need suggestion for data transformation
> Here is the ditribution of a measurement:
> 
>        snk_r1    Frequency     Percent
>                 ------------------------
>            0        1750       91.62
>  0    ~ 0.04          55        2.88
>  0.04 ~ 0.08          55        2.88
>  0.08 ~ 0.12          22        1.15
>       > 0.12          28        1.47
> 
> 
> This data is seriously biased to zero. I wonder
> whether there is any good method to transform
> this measurement and make its distribution into
> normal distribution, and how to do in stata.
> 

*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index