ABSTRACT
While measurement precision is relatively easy to establish for single tests and assessments, it is much more difficult to determine for decision making with multiple tests on different subjects. This latter is the situation in the system of final examinations for secondary education in the Netherlands and is used as an example in this paper. This examination system consists of several school-specific and central parts. A method is presented for quantifying measurement precision for multiple tests in terms of a classification table of true and observed classifications. With this method the percentage of students that is either correctly or incorrectly classified by the tests being administered can be estimated. The method is used to assess the effects of different pass/fail decision rules by application to data from high stakes examinations in pre-university education in 2008. The results are mixed, but generally indicate good properties of compensatory aspects of decision rules. Implications of the results are discussed.
