Resources and other notes from eCOTS 2020
(Work in progress) A collection of notes, resources, recommendations and more from eCOTS 2020 (Electronic Conference on Teaching Statistics). See the full program here.
Liza’s one sentence summary
These are my session notes from my first ECOTS experience, as well as a list of resources to help me keep track of all the things I want to check after this conference, that I hope might help you too.
W01: Multivariable thinking across the curriculum
Beth Chance, Elena Keeling, Karen McGaughey, Jamie Bunting (Cal Poly, San Luis Obispo); Nathan Tintle (Dordt University)
I love the idea of the two bogs! I think it would be interesting to ask students which bog they’re more at risk of falling in…
Source: [Tintle et. al. (2015)](#combating-anti-statistical-thinking-using-simulation-based-methods-throughout-the-undergraduate-curriculum
Bog of overconfidence
- Over emphasise p-value criteria
Bog of disbelief
- Hope for a miracle
- Not understanding what is going on behind the scenes
- Hope for a miracle
Examples from biology
- Making sure language is consistent across the Statistics and Biology courses students are taking so that their aren’t barriers to understanding. “Statisticians & biologists use the same words to mean different things, and different ords to mean teh same things”.
- Statistical signficance vs. biological revelance. The connections and distinctions needs to be made clear.
Statistical Thinking in Undergraduate Biology project: http://www.causeweb.org/stub
Multivariable thinking in a second statistics course
- Thinking about sources of variation
- Have students predicts changes with data visualisations, show blocking/confounding
- A second stats course is often taught as disparate methods, how do you weave this together into a unified approach?
Multivariable thinking in an introductory statistics course
I especially likes the emphaisis on discussing things like study design, sources of variation, as a way to ‘engage everyone’ (theme of this eCOTS), as it opens up contributions from a wider range of students. I also think this is tha path to
Advice on finding datasets
- Keep an eye on teh NYT Science section
Engaging Everyone: Context, Communication, Connections and Commitment
Roxy Peck, Professor Emeritas, Cal Poly, San Luis Obispo
- Some contexts may be disruptive to learnign for some students. Examples given: depression, immigration status.
- Choose a path homework problems.
- Multiple datasets. Students asked to do the same things for each, but could pick the context they were interested in.
- Student question bank competition
- We’re all a little interested in ourselves. Journal of College Student development can be a good source. https://www.press.jhu.edu/journals/journal-college-student-development
Questions prompts for students
- What surprised you?
- What did you find most interesting?
- Do you have any experience with this in your life?
Challenge and guide thinking: https://askgoodquestions.blog/
Our job is to create opportunites for student learning and the development of conceptual understanding.
“Lecturing at the bored”
Groupwork Pedagogy for Addressing Classroom Social Inequalities
Alana Unfried & Judith Canner (California State University, Monterey Bay)
- Managing status indicators in the classroom.
- Intructors as manager of student relationship to content, not as conduit to content.
Source: Unfried & Canner slides
Norms, roles and participation structures**
- Create as a class a set of norms
- Assign students specific roles in the group
- Randomly assign people to groups
- “Groupworthy tasks” are open-ended, uncertain, have multiple entry points and cover an intellectually important component.
- Paper airplane protocal activity requires a range of skills.
- If status is not managed, you will have unequal participation.
Challenge the idea that it is just lack of motivation. Student self-concept and perception from other group members can be a big issue.
Open-Ended Data Analysis Collaboration in the Introductory Statistics Course
Rebecca Nugent & Philipp Burckhardt (Carnegie Mellon University)
- Fabulous example about how important human subjectice decisions matter in data analysis. *Source:
- Have had students copy friends code and say “look, it is reproducible!”
Dollar Street Contest Winners
2020-05-19 11:30 and 12:15 Winners: Stacey Hancock & Jade Schmidt; Erin Freeman
I’m looking forward to going back and taking a look at both of the winning presentations. Some great tips about desining these sessions and how to support student thinking. I’ve long been a fan of Gapminder and Dollar Street but haven’t had a chance to use it in teaching yet. This was a great prompt to get me thinking about how to use it in future.
Engaging Everyone with Clickers
2020-05-19 13:00 Kari Lock Morgan (Pennsylvania State University)
- Repitition is important for learning, but instead of just repeating yourself, teach something and then use a personal response system to have students “think it back at you”.
- Love the priming example! (Even/odd birthday athletes/singers).
Engaging curiosity! You didn’t care about the fish example until you had to come to an opinion/prediction of what would happen.
- This looked awesome but I had to skip out to let out building manager in to see what idiotic way I had broken the dishwasher. Really looking forward to watching the recording.
- Edgar Dale’s Cone of Experience discussion especially was of great interest to me.
These are just some Tweets I appreciated and wanted to come back to later.
From the #eCOTS2020 workshop on multivariable thinking: Walk through the 6 steps of a real-world analysis on the first day of an intro class. It gets students to ask questions and realize they can make a contribution in statistics from the beginning. pic.twitter.com/01iCIzrvhm— Maria Tackett (@MT_statistics) May 18, 2020
Combating anti-statistical thinking using simulation-based methods throughout the undergraduate curriculum
Tintle, Nathan & Chance, Beth & Cobb, George & Roy, Soma & Swanson, Todd & VanderStoep, Jill. (2015). Combating anti-statistical thinking using simulation-based methods throughout the undergraduate curriculum. The American Statistician. 69. 10.1080/00031305.2015.1081619.
The use of simulation-based methods for introducing inference is growing in popularity for the Stat 101 course, due in part to increasing evidence of the methods ability to improve students’ statistical thinking. This impact comes from simulation-based methods (a) clearly presenting the overarching logic of inference, (b) strengthening ties between statistics and probability or mathematical concepts, (c) encouraging a focus on the entire research process, (d) facilitating student thinking about advanced statistical concepts, (e) allowing more time to explore, do, and talk about real research and messy data, and (f) acting as a firmer foundation on which to build statistical intuition.
Thus, we argue that simulation-based inference should be an entry point to an undergraduate statistics program for all students, and that simulation-based inference should be used throughout all undergraduate statistics courses. In order to achieve this goal and fully recognize the benefits of simulation-based inference on the undergraduate statistics program we will need to break free of historical forces tying undergraduate statistics curricula to mathematics, consider radical and innovative new pedagogical approaches in our courses, fully implement assessment-driven content innovations, and embrace computation throughout the curriculum.
- Simulation-based inference blog: https://www.causeweb.org/sbi/