Wednesday, March 30, 2011

Campbell's Law

This is a useful adage to have on hand when any discussion turns toward statistics:
The more any quantitative social indicator is used for social decision-making, the more subject it will be to corruption pressures and the more apt it will be to distort and corrupt the social processes it is intended to monitor.
I just encountered this "law" in the context of education reform, because it seems that the more stress you put on test results, the more cheating you get. Or, more broadly, the more you stress test results, the more effort people put into getting higher scores by any means necessary rather than on teaching whatever the test is supposed to measure.

This doesn't mean that the purpose of standardized testing will always be defeated, it just means you have to work very hard to develop good tests and monitor the results for cheating.

No comments: