Microsoft Word 2007 ichrie conference Proceedings Final-Final 06-06-07. doc

 
is
 
a matrix of variables as per Beneish 
(1999a); and 
ε
i
 
represents the residual in the regression. It should be noted that we used two different variables for 
the Beneish index. One used eight ratios while the other used ten ratios.

---

 
2007 Annual International CHRIE Conference & Exposition 
478
RESULTS 
Before running the regressions, we obtained summary statistics and correlation coefficients for the 
variables, shown on Tables 1 and 2. Marcpata was not significantly related to either of the Beneish indices or 
CFTA, the other control variable. CFTA is significantly related to Beneish 10 index. However the absolute value of 
the correlation at 0.5 was much below 0.8, which could cause multicollinearity problems. As expected, there is a 
significant correlation between both the Beneish indices. However, they are not entering into the model at the same 
time, and even then the magnitude at 0.49 is less than 0.8.