Abstract:

In the Slovakia today, there is great interest in the education and graduation of more students in the Science, Technology, Engineering, and Mathematics (STEM) disciplines. Once those students are attracted to a STEM field, the colleges and universities must provide an attractive, nurturing environment designed to allow a wide range of students to succeed, while still providing a rigorous education. That is a big challenge, because many first-year university students are struggling to pass mathematical subjects, especially those studying in quantitative areas such as engineering and science. Despite the importance of mathematical skills in quantitative disciplines, high failure rates in first-year university mathematics subjects have been observed in many parts of the world, in Slovakia as well. To improve retention in first-year mathematics students, a new teaching model extensively using digital technology was implemented at Faculty of Material Science and Technology of Slovak University of Technology. Multi-component assessment, serving in formative as well as summative way, is one of core components of that model.

Presented research study deals with validity of during-term e- assessment of students in introductory university mathematics course. During-term e-assessment is conducted to make judgments as to whether students have achieved the learning outcomes of the particular course stage and for the purposes of grading and further progression in course, as well. Results of assessment are used by students for further learning path (formative use), as well as, are used for calculating final students´ course grade (summative use), therefore during-term assessment has to provide valid information for both students and teachers.

To check up validity of e-assessment, an experiment was performed in that assessment. Results were compared on performance scores using the same conditions in test and retest. Those students (153 from 404 students), which obtain low performance score, retake the during-term test after six weeks to determine if they then improve their scores. Performance scores were found not to differ depending on whether the assessment was completed in the first run or re –run mode. Surprisingly, mean performance scores in five from six topics covered by test were slightly lower in retest than in test. These findings provide support for the validity of proposed e-assessment methods. Future studies could help determine the extent to which this finding generalizes beyond the assessment procedures and type of sample used here.

Keywords:

E-assessment, validity, mathematics.