A method is described for monitoring teachers’ grade standards in Certificate of Secondary Education examinations. The power of this method to detect various degrees of error in grade standards is estimated using real data. In certain circumstances, the expectation is that more than a third of the candidates taking an examination will be mis-graded due to the low power of the statistical test on which the method depends.
Get full access to this article
View all access options for this article.
References
1.
HoggR. V., and CraigA. T.. (1971), Introduction to Mathematical Statistics (third edition). London: Macmillan.