摘要：To ensure fairness, test designers and developers strive to make their instruments for assessing the language abilities of learners as accurate and reliable as possible, and have traditionally used a number of techniques to ensure this. From a post-modern, and especially critical perspective, however, these measures are not enough to ensure fairness. In these approaches, fairness is redefined and reconceptualised. This article demonstrates that it is still possible to use conventional techniques to achieve the goal of, for example, increasing the accessibility of a test. Using several statistical analyses of the results of a test of academic literacy as examples, the article concludes that traditional, quantitative measures enhance and complement, rather than undermine, current concerns.
其他摘要：To ensure fairness, test designers and developers strive to make their instruments for assessing the language abilities of learners as accurate and reliable as possible, and have traditionally used a number of techniques to ensure this. From a post-modern, and especially critical perspective, however, these measures are not enough to ensure fairness. In these approaches, fairness is redefined and reconceptualised. This article demonstrates that it is still possible to use conventional techniques to achieve the goal of, for example, increasing the accessibility of a test. Using several statistical analyses of the results of a test of academic literacy as examples, the article concludes that traditional, quantitative measures enhance and complement, rather than undermine, current concerns.
