EJMT Abstract

In this article, the assumption is made that the use of a suitable quantitative data analysis method can increase the reliability of the results presented in research. In this context, it is the goal of this article to present an alternate proposal for quantitative data analysis that aggregates information and that is compatible with the qualitative approach of Didactic Engineering. This methodology, like all methodologies of qualitative research, rejects the resources of Classical Statistics, such as parametric analysis, the control case, or experimental groups and control groups. The validation method of Didactic Engineering is internal. The analyses are based on the comparison between the a priori and the a posteriori analyses. Considering that it is worth discussing such a rejection, an alternative resource for the use of formalized tests in the theory of Non-Parametric Statistics is presented. The justification is that this resource does not require a population model, and does not require a large number of hypotheses. In addition, Non-Parametric Statistics provides the Didactic Engineering methodology with a treatment that meets the prerogative of falsifiability in Popper’s scientific method. This argument is based on theories of mixed methods research and complementarity.