The 21st century challenge for science education: Assessing scientific reasoning

Expectations of the outcomes of education in the 21st century increasingly focus on higher order thinking of synthesis, analysis and evaluation. Yet school science education is still dominated by lower level cognitive demands in particular recall. The argument made by this paper is that the failure to transform science education for the needs of the 21st century is a consequence of a lack of a good model of scientific reasoning and a body of expertise about how to assess such higher order cognitive competencies. In response, this paper presents a model for scientific reasoning which is a synthesis of contemporary philosophical perspectives and empirical psychological studies of how scientists work. Such a model offers some insights into the kind of competencies that science education might seek to develop to address the contemporary demands of society. Scientific reasoning is, however, domain specific and dependent on a knowledge of the content and concepts of science; a body of procedural knowledge about standard methods; and an epistemic knowledge of how such procedures warrant the claims that scientists advance. Assessing 'what counts' depends on a deeper understanding of what counts in this case the nature of the performance and the knowledge base required for the display of higher-order thinking reasoning. Finally, it is argued that recent developments in computer-based platforms such as the open-source TAO platform to be used for the PISA assessment in 2015 and other computer-based platforms offer the promise of enabling students to display a wider range of performances and more sophisticated methods of assessments. Better assessments are not possible, however, without better constructs and likewise, better constructs cannot be assessed without a broader repertoire of methods of assessing student performance. (C) 2013 Elsevier Ltd. All rights reserved.