This is a session of Topic 6: Innovation and reform in teaching probability within statistics
(Thursday 17th, 10:55-12:25)
Probability and p-values — probing the problems
- Robyn Reaburn (Australia) : Session chair
For students to understand inferential statistics an understanding of probability is required. Research shows, however, that many students have poor understanding of probability when they commence the study of statistics at tertiary level. This becomes a problem when students are asked to carry out hypothesis testing using p-values. Some students become confused, and as a result develop the idea that a p-value is the probability that the null hypothesis is true. Once this misconception is developed, it is difficult for students to adapt their thinking.
This session examines the research into students’ understanding of probability and conditional probability during their education. The session also describes the research pertaining to how instructors encourage their students to understand the process of null hypothesis yesting and the meaning of p-values. In particular, there will be an examination of the role of computer simulation in assisting students to understand these topics. This session will also examine the debate around the effectiveness of p-values compared to the use of confidence intervals when interpreting the results of null hypothesis tests. Other issues related to the difficulties associated with probability, p-values and decision making may be introduced by presenters.
|Paper||Title||Presenter / Co-author(s)|
|6B1||Impact of a simulation/randomization-based curriculum on student understanding of p-values and confidence intervals||Beth Chance (United States)|
Karen McGaughey (United States)
|6B2||Teaching probability: using levels of dialogue and proportional reasoning||Ian Hay (Australia)|
|6B3||The interpretation of effect size in published articles||Rink Hoekstra (The Netherlands)|