Abstract:

The new educational model implemented in the Spanish University, attaches great importance to the implementation of continuous assessments. This model requires the student to carry different tasks along the course, either individually or in groups.
The statistical subjects, in most Grades are structured into theoretical-practical classes in which the student works the different problems “by hand”, and into laboratory classes with computers. So, two types of tasks can be planned for the continuous assessments; problems to solve “by hand”, and problems to solve with the help of an statistical specialized software. Anyway, four points must be outlined, regarding these continuous assessments: a) Professor must increase considerably his/her daily work, because of the amount of material that must be corrected and returned to the students for a correct feed-back. b) Even in the case of individual tasks, if the same task is proposed for the whole group, students tend to solve it jointly in groups, and present it later individually, so the teacher finds (and corrects) exactly the same task several times. c) Other students directly copy the task performed by other mates, and the sense of the continuous assessment is completely lost d) If slightly different tasks must be prepared for each student, the amount work for the teacher increases both, in the preparation of the task and in its correction. So in this work we would like to propose specialized software that could help us in: a) preparing automatically individual tasks for the students of statistical subjects; b) a same task must be different for the different students (different data sets, different assumptions,…); c) correction must be automatically done; d) it must offer an easy feed-back process to students.
During this course, we have began to explore the different possibilities that offers specialized GNU-software such as the “Auto Multiple Choice” [1], and the combination of different LATEX packages such as Sweave [2] and R [3]. In this work, we would like to comment our experience with both software, signaling their strengths and weaknesses (in our opinion), and analyzing the results of this experience, from the point of view of both students and teachers.

References
[1] Auto Multiple Choice. http://home.gna.org/auto-qcm/index.en. Friedrich Leisch. Sweave: Dynamic generation of statistical reports using literate data analysis. In Wolfgang Härdle and Bernd Rönz, editors, Compstat 2002 - Proceedings in Computational Statistics, pages 575-580. Physica Verlag, Heidelberg, 2002. ISBN 3-7908-1517-9

[2] http://www.stat.uni-muenchen.de/~leisch/Sweave/

[3]R: A Language and Environment for Statistical Computing. R Foundation for Statistical
Computing, Vienna, Austria, 2012, ISBN 3-900051-07-0,http://www.R-project.org/.

Keywords:

Continuous assessments, Statistics, Individualized tasks.