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

Re: st: a statistical question.


From   Joseph Coveney <jcoveney@bigplanet.com>
To   Statalist <statalist@hsphsun2.harvard.edu>
Subject   Re: st: a statistical question.
Date   Sun, 13 Jun 2004 13:13:44 +0900

>generally speaking,if i want to do a chi2 test,the expacted count of each cell 
>should more than 5.but if i have less,what statistical test should i take? is 
>fisher's exact test a good idea?

There's controversy among the experts about both the rule of thumb and whether 
Fisher's exact test is best (see, for example, 
http://www.math.yorku.ca/Who/Faculty/Monette/S-news/0669.html ).  But in most 
cases, it probably doesn't matter greatly.

>my data table is as follow,and if i use exact test ,the p-valuve is 0.00.is 
>it wise to use it? thank you !
>
>	col
>row	1	2	3	Total
>				
>1	6	12	2	20 
>2	18	68	43	129 
>3	9	4	1	14 
>				
>Total	33	84	46	163 

I recommend avoiding stating p-values as equal to zero.  Rather, I recommend in 
this case stating it as "P<0.005" if you don't know it with any more precision. 
 If you're using Stata (-tabulate row col, exact-), then you can get the value 
by typing -return list-, which in the case of this table is 0.0002.

Joseph Coveney


*
*   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