Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: programming prob


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: programming prob
Date   Fri, 11 Apr 2008 18:34:55 +0100

If an option is not compulsory, the -syntax- specification (in your
case) would be 
-sig(real 0.95)-. You missed out "real". 

If you are interested in testing for normality, look at -omninorm- from
SSC. 

Despite my joint authorship of the above program, I declare a prejudice
that testing 
for normality is one of the most over-rated statistical activities! 

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

Martin Weiss

Does not work, either...

Maarten buis 

--- Martin Weiss <martin.weiss@uni-tuebingen.de> wrote:
> I wanna check the power of normality tests and to this end I have
> written a program that does exactly that. It worked fine until I
> added an option to provide a desired sig. level to the program.
> Stata complains about the syntax, and I cannot figure out why.
> Any ideas why that might be? I want to make both varlist and sig
> optional so I put them in square brackets.  Here is
> the program (with useful commands around it):
> 
> *********
>   capt pr drop normality
>   
>   pr de normality, rclass
>         version 10
>         syntax [varlist(max=1 numeric default=none), sig(0.95)] 
<snip>

This should be:
syntax [varlist(max=1 numeric default=none)], [sig(0.95)] 


*
*   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/



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