On 3 Nov 2003 07:05:23 -0800, [EMAIL PROTECTED] (VOLTOLINI) wrote:

 ... 
> I heard from a colleague that....
> 
> When the Ho of independence is rejected in a contingency table 
> you can compare the partial chi-square values with the 
> chi-square value from the table to check if there is one or more 
> partial chi-square values that could reject the Ho alone. 
> 
> Is it true? 
> 
> I cannot find this idea in any classic stats text book :(

Is this what you mean by partial chi-square?

When you have a table where the test is the sum of
the contributions of the cells, you *can*  look at the
cells to see what each cell  contributes.  Sometimes
that is convenient for describing the effect.

Does that tell you what is changing?  - not always.

Look what happens  in a 2x2 table:  every cell has the
X2_i =  (Obs. minus  Exp.)  which is exactly the same.  
The 'contribution'  is biggest for the smaller row and column.
That does not prove that the logic, or the dynamics of 
whatever is taking place, has to focus on that cell.

-- 
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
"Taxes are the price we pay for civilization." 
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to