Catalysts to Present at February Stat Chat

The spring session of Stat Chat continues on Tuesday February 22, 2011. Stat Chat is an informal, but informative, monthly get-together of local statistics educators. We meet in room 205 of the Olin-Rice Science Center at Macalester College [See Map].


The agenda for this Stat Chat is as follows:

• 6:00 - 6:30, Dinner (and warm up activity to introduce the CATALST philosophy)
• 6:30 - 7:00, Journal Club: The Introductory Statistics Course: A Ptolemaic Curriculum?
• 7:00 - 8:00, Main Event: The CATALST Course (Joan Garfield, Robert delMas, Laura Le, Rebekah Isaak, Laura Ziegler, Andy Zieffler)

During this month's journal club (see below), we will discuss George Cobb's paper The Introductory Statistics Course: A Ptolemaic Curriculum? This paper was the inspiration for the CATALST course, which will be the topic of this month's main event. CATALST is an NSF-funded project that has created a curriculum designed to develop students’ statistical thinking and appreciation of statistics through a focus on modeling, simulation and inference. The CATALST curriculum is currently being taught in several sections of undergraduate-level statistics at the University of Minnesota and at North Carolina State.


We will share an overview of the curriculum, as well as a sample of class activities used in the course. Specifically, an activity used to introduce the randomization test for group inferences will be shared. The software TinkerPlots™, which is used by students in the course to conduct the modeling and simulation, will also be demonstrated.


PLEASE RSVP to Danny Kaplan so that we can plan sensibly for dinner. As always, last-minute deciders and guests are welcome.

Journal Club

Journal club was introduced at Stat Chat during the 2009-2010 academic year as a venue for discussing articles, books, etc. with other statistics educators. The following online resources are provided for this month's discussion of The Introductory Statistics Course: A Ptolemaic Curriculum?

• The Introductory Statistics Course: A Ptolemaic Curriculum? by George Cobb [Read Article]

Some discussion questions:

•  In the article, George posits that randomization-based inference deserves to be at the core of every introductory course. Do you agree? Why or why not?
• If someone decides to teach using randomization methods, is it necessary to still teach classical methods (e.g., the t-test) in addition to randomization methods? Or can these be introduced as an aside?
• George argues that technology has freed us to simplify our curriculum. Is this true? Or has it merely shifted the focus? Has it in fact made things more complex because we now have an obligation to teach computing as well?
• What should the balance be between teaching statistics and teaching computing?

Community...Dependence...Better!

From Seth Godin's blog

Self sufficiency appears to be a worthy goal, but it's now impossible if you want to actually get anything done. All our productivity, leverage and insight comes from being part of a community, not apart from it. The goal, I think, is to figure out how to become more dependent, not less. 

Catalysts in Japan

Seeking Adventurous Statistics Teachers

The NSF-funded CATALST (Change Agents for Teaching and Learning Statistics) project is looking for a few courageous statistics instructors willing to adapt and implement a radically different introductory statistics course. Based on ideas put forth by George Cobb in his 2005 USCOTS plenary talk and his 2007 TISE paper, a unique course has been created to develop students’ statistical thinking and appreciation of statistics.

What is unique about this course? Rather than teaching students to follow recipes, the curriculum engages students in the process of statistical thinking that allows them to really cook. By keeping the focus of the curriculum exclusively on modeling and simulation the emphasis from the first day in the course is kept on key statistical ideas such as the importance of data collection methods, variation under uncertainty (random sampling vs. random assignment), the ideas of null and alternative models, and a deep understanding of the process statistical inference.

Students are introduced to randomization and bootstrap methods to help draw inferences. The curriculum includes content for inferences regarding means and proportions and for both one- and two-sample comparisons. Students conduct all of the modeling and simulation–including the randomization and bootstrap methods–using the TinkerPlots software.

 Because the course uses technology to carry out these simulations, many concepts can be understood from empirical evidence, with less reliance on mathematical theory and computing rules. As a result, some traditional topics such as computing areas under the normal curve, z-scores, and the Central Limit Theorem are less necessary, and have been removed to make more time for concepts at the core of inference.

This course is currently being piloted at both the University of Minnesota and North Carolina State University. We are looking for people who want to become CATALST collaborators by adapting and using this course in one of the following settings:

1. A statistics course for pre-service teachers
2. A freshman seminar
3. A statistical or quantitative literacy course
4. A basic introductory statistics course
5. An introductory course for students in the sciences
6. An online class
7. A course that enrolls large numbers of students

What we have to offer: Some stipends to reward you for taking the time to work on adapting and implementing this course, the opportunity to collaborate with an enthusiastic team of statistics educators, the opportunity to create a unique version of the CATALST course that others may use, and the opportunity to collect meaningful data that help you (and us) see how well your students are learning to think statistically and understand the big ideas of statistical inference.

Are you interested? Would you like to join our collaboration? Would you be willing and able to adapt and teach this course next year? Would you be willing to come to a pre-USCOTS meeting in Raleigh, North Carolina (Thursday May 19, 1:30-3:30) to meet with the CATALST team?

If so, please contact Joan Garfield to express your interest. We can share with you our current course outline, syllabus and activities. We are looking for people to keep the bulk of the course intact, but perhaps collapse the second and third unit into one unit and add additional material if needed.

Be sure to check out the CATALST project at: http://www.tc.umn.edu/~catalst/