PROCEEDINGS OF THE 15TH ANNUAL CONFERENCE ON RESEARCH IN UNDERGRADUATE MATHEMATICS EDUCATION (Vol 1)
2012
Portland, Oregon
To Reject or Not to Reject: One Student’s Non-Normative Decision Procedure for Testing a Null Hypothesis
Page: 1-315
The purpose of this study was to gain insight into how exposure to hands-on and computer resampling methods affected a statistically naïve student’s emergent understandings of statistical inference. In this study, simulation design activities provided a vehicle for engaging a student with the core ideas of hypothesis testing. The results highlight challenges the student experienced in coordinating the components of the logic into a coherent scheme of ideas and sheds light on aspects of engagement which need to be emphasized in order to resolve the inherent conceptual difficulties associated with reasoning that invokes a modus tollens-like argument. Moreover, I report on a heuristic the student used to make his inferential decisions—one that does not produce correct inferences. I’ve termed this the “similarity heuristic” because of a specific similarity relationship the student would look for and then use as a method for rejecting or not rejecting the hypothesis being tested.