For more immediate conversations about these issues, also consider joining the Simulation-Based Inference Listserv. The SBI mailing list is intended for individuals interested in discussing pedagogical issues related to using simulation-based inference techniques (e.g., randomization tests) in introductory statistics courses as the primary introduction to statistical inference. For more information or to subscribe, go to https://www.causeweb.org/mailman/listinfo/sbi.
We are looking for individuals/institutions willing to give common assessment items during Winter/Spring 2015.
- Pre/Post attitude surveys (SATS)
- Pre/Post concept inventory (modeled after CAOS and GOALS)
- Embedded multiple choice exam questions (Unit 1: One Proportion, Unit 2: Two Proportions and/or Two Means)
We will send you names of students who participated (if you want to give course credit) as well as a report at the end of the term with your student results and comparison results. For more information, please contact Cindy Nederhoff <Cindy.Nederhoff@dordt.edu>.
Beth Chance, Nathan Tintle, and the ISI team
Although we strongly agree that we must do more to help students understand the role of sampling variability in inferential decisions, we have not yet been convinced that a formal treatment of bootstrapping (having students sample with replacement) is the only path to get them there.[pullquote]we worry that the motivation for conducting bootstrapping is less intuitive for students[/pullquote] Continue reading
|Introduction to Statistical Investigations
ISI Discussion Board Forum
|Statistics: Unlocking the power of data|
|Statistical Reasoning in Sports|
|Statistical Thinking: A simulation approach to modeling uncertainty|
|Intro Stat with Randomization and Simulation|
|Investigating Statistical Concepts, Applications, and Methods|
Beth Chance, Cal Poly – San Luis Obispo
My technology use has definitely evolved, including in ways that surprise me! In particular, I have switched from being a long-time advocate of Minitab to not using a standard statistical package in the course at all. In reflecting on why this was the case, I realized I had some guiding principles: [pullquote]I want student to see simulation-based methods as equally legitimate to theory-based procedures, if not preferred in some situations. [/pullquote]
As part of our NSF grant (DUE #1323210, Nathan Tintle, Principal Investigator), we are hosting this blog to contribute to the development of an online learning community for instructors.