The SCheck program
The g2 collusion index seen in Integrity stems from what Wesolowsky (2000) has referred to as the “seminal work” of Frary, Tideman, and Watts (1977). Wesolowsky’s paper presented a modification to Frary et al.
In researching Wesolowsky’s modification, Tideman and Kheirandish (2003) found it had “noticeably better power than the probabilities suggested by Frary et al.”.
Better power means that Wesolowsky’s method has a greater likelihood of rejecting the responseindependence hypothesis if the hypothesis is in fact false – it is more capable of detecting possible cheating, less likely to make a Type II error.
Returning to the test center A data set discussed above, SCheck rejected the response-independence hypothesis for the first two cases seen in Table 1, whereas g2 rejected only the first of these two – this may be an example of SCheck’s superior statistical power.