Quality is an overall test measure, derived from quality of norms (norm), hardness (hard), resolution (res), validity (val), reliability (rel), and robustness (rob) as follows:
Quality = norm × hard × res × val × rel × (1 - rob)
For robustness, (1 - rob) is used to reverse the negative measure and make it start at 0. As a measure of validity, the estimated g factor loading is used in the case of intelligence tests.
The previous scaling from 0 to 1 has been abandoned for being too arbitrary. The new Quality has no upper limit and starts at 0.
Quality is an overall test measure, derived from robustness (rob), validity (val), reliability (rel), hardness (hard), resolution (res) and quality of norms (norm) as follows:
Test quality = √((rob2 + val2 + rel2 + hard2 + res2 + norm2) / 6)
As a measure of validity, the estimated g factor loading is used in the case of intelligence tests. When one or more of the statistics is or are missing they may be left out and the divider adjusted appropriately.