>>> John Boone on Ethics 
 WE> First off the statistics are not complete.  You have to do 
 WE> a chi-squared test to determine the significance of any  
 WE> discrepancies.  If a likely bias is determined it makes no  
 JB> 
 JB> The chi-squared test is used to give an idea how likely the 
 JB> difference arises from chance alone
Correct.
 WE> difference whether the bias is blatant social bias or from 
 WE> some other systematic cause such as being unable to afford  
 WE> defense.  The determination of the cause is issue for  
 WE> further study, not all necessarily mathematical.   
 JB> Now, if you considered the number of arrests 
 JB> to the number of convictions in each group and 
 JB> compared those ratios, a bias would become more 
 JB> apparent as the ratios should be nearly equal.   
 JB> 
 JB> The words "bias would become more apparent as the ratios 
 JB> apparent as the ratios should be nearly equal" imply 
 JB> differences in ratios would be due to bias, "systemic 
 JB> error, resulting in over or underestimation of the 
 JB> strength of the association."  When, in fact, WITHOUT 
 JB> BIAS, differences in ratios may in fact be due causation, 
 JB> etc without "systemic error, resulting in over or underestimation 
 JB> of the strength of the association."   
I didn't claim that bias would be determined.  I indicated that by refining 
the data bias would be easier to determine.  Also note my statement above 
that indicates how 'noise' in the data needs to be considered.
... UFO - Unduly Fabricated Opinion from inner space.
---
---------------