Friday, March 21, 2014

Dr. Everson speaks to ASA Twin Cities about 10 years teaching statistics online

Yesterday's meeting of the American Statistical Association, Twin Cities Chapter was focused on a subject very dear to us Catalysts: statistics education!  Milo Schield of Augsburg College opened the evening by discussing "Two Big Ideas for Teaching Big Data", reflecting on the importance of causation and confounding especially in a world of data-driven decision making where the data is observational, and every association is "statistically significant."

Our Michelle Everson then spoke about the lessons she's learned from her ten years of online statistics instruction.  How do you foster active learning in the online classroom?  How do you keep the work manageable?  How involved should you be in discussion?  As someone constantly experimenting and critiquing her own techniques, Dr. Everson didn't present final answers to these questions, but she did share her accumulated wisdom from her online journey:

Tuesday, January 21, 2014

Joint Mathematics Meetings

Nicola Parker and Andy Zieffler went to Baltimore, MD to participate in the Joint Mathematics Meetings on January 15–18, 2014. 

Besides attending the Joint Meetings, they also gave a 4-hour minicourse on the CATALST course. The minicourse included 14 enthusiastic participants from colleges and universities across the country (and even a high school teacher!). Even though the second-half of the minicourse took place on Saturday afternoon—the last day of the conference—all of the participants came back, and we even gained a participant. We think it was quite a success and have been invited to return and repeat it again next year at the 2015 Joint Meetings in San Antonio!

Nicola mesmorizes the minicourse participants with TinkerPlots.
The meetings were well attended and included a Contributed Paper Session sponsored by the Statistics Education SIGMAAA—Data, Modeling, and Computing in the Introductory Statistics Course. Catherine Case and Melanie Battle gave a nice talk, Toward a Conceptual Understanding of P-values: The Advantages and Challenges of Randomization-Based Inference, which referenced some of the research that has come out of the CATALST project. In addition, Nick Horton's talk, Big Data in the Intro Stats Class: Use of the Airline Delays Dataset to Expose Students to a Real-World, Complex Dataset, also gave a plug for CATALST, making use of the Comparing Airlines MEA that is the initial activity in Unit 2 of the CATALST book.

Catherine Case and Melanie Battle, graduate students at the University of Florida, gave a nice talk on students' understanding of p-value when implementing randomization methods in introductory statistics courses and referenced CATALST.

HHMI Curricular Collaborations Meeting

On January 13–15, 2014, Laura Le, Laura Ziegler, and Andy Zieffler participated in the HHMI Curricular Collaborations meeting that took place at the Howard Hughes Medical Initiative center in Chevy Chase, MD. The meeting included HHMI grant awardees whose grant focus was on curricular innovation through multi-institution collaboration.

Laura and Laura "re-sample" poses from the Harmon Trophy which was awarded to Howard Hughes in 1936 and 1938 as the world's most outstanding aviator.

Our work is building and evaluating an assessment of quantitative skills and reasoning for biology students. This work started in June, 2013 when science educator/researchers from several liberal arts colleges—the grant includes Bryn Maar, Claremont McKenna, Emory, Harvey Mudd, Lewis & Clark, Macalester, Morehouse, Oberlin, and St. Olaf—gathered to brainstorm in Portland, OR. The conversations in Portland led to an initial version of an instrument that was piloted at many of these schools.

This meeting we spent several more hours refining both our vision/goal for the instrument. Pilot results were used to also help further flesh out the instrument. Next steps include making revisions and a second piloting.

We had several speakers and learned about many different projects throughout the meetings, including learning about the new MCAT, which will be administered starting in 2016.

Monday, December 9, 2013

Omnipresent variation in visions of the future introductory statistics textbook

The latest issue of Technology Innovations of Statistics Education, edited by Rob Gould of the University of California at Los Angeles, presents three very distinct visions of the the possibilities for a future statistics textbook. These articles are based on a session organized by Joan Garfield at the 2011 Joint Statistical Meetings, in Miami, Florda.

Three members of the CATALST team—Andrew Zieffler, Rebekah Isaak, and Joan Garfield—discuss the role of textbook in developing an introductory undergraduate course based on using simulation, randomization, and the bootstrap to develop the core logic of inference.

The innovation is primarily pedagogical. Zieffler et al. discuss how they found that having a unified, structured document to be very useful in supporting students' learning in an activity-based, student-centered course. The latest version of the textbook is available for free from Catalyst Press under a Creative Commons license which allows modification and incorporation of the material in for-profit works. (See our previous post on this book). The article discusses future plans for further innovations to the book such as incorporating videos directly into an e-book.

Cetinkaya-Rundel, Diez, and Barr also present a free product, OpenIntro Statistics, which is totally open source (the source code is fully available for modification). Their approach is based on a normal-theory based approach to the introductory course, chosen to encourage wide adoption, and the authors discuss the advantage inherent in having such a radically open process for development.

Webster West of North Carolina State University presents a vision that is more technologically intensive, including algorithmically generated exercises and tight integration of the textbook with the course management system and analysis software. His experiences partnering with Pearson Education and developing StatCrunch speak to how one might integrate technology with widely used, mainstream textbooks (though he describes himself as "closet radical").

The whole issue is well worth reading, because it features some lively and skeptical comments representing conflicting opinions from statistics education luminaries Beth Chance and Allan Rossman, George Cobb, Paul Velleman, and Jessica Utts, followed by responses from the authors.

Thursday, October 10, 2013

Social Media and Statistics Education

Dr. Michelle Everson is helping to catalyze new directions in statistics education through social media and the online classroom.

Social networks such as Facebook and Twitter provide not only distractions, but also great opportunities.  Building on her work in online classrooms and her teaching experiments that incorporate social media, the University of Minnesota's Michelle Everson provides some tips and resources for using social media to teach some resources in the latest AMSTAT News. She candidly shares both the successes and failures that she's experienced using these approaches.

For a deeper dive, Michelle has also recently published an overview of the pedagogy of social media in the latest issue of Computers and Human Behavior, with coauthors Ellen Gundlach of Purdue University, and Jaqueline Miller of Ohio State University.  Entering the maelstrom of social media is a bit easier with these thoughtful and seasoned teachers to guide you!

Monday, September 23, 2013

SRTL-8: Great Discussions by a Great Lake

Great statistics education thinkers from around the world came to sleepy Two Harbors, Minnesota for a week of discussion, debate, and reflection on the great issues in our field. The theme of the Eighth Forum of the International Collaboration for Research on Statistical Reasoning Thinking and Literacy (SRTL-8) was: Reasoning about uncertainty in the context of making informal statistical inferences. Our explorations of students' reasoning about uncertainty included many videos of students working through problems, and we explored the process of informal inferences qualitatively and quantitatively among K–12 and undergraduate students and teachers.
Twenty-four international delegates attended the week-long event from nine countries across the globe: Australia, Colombia, Germany, Israel, the Netherlands, New Zealand, Turkey, the United Kingdom, and the United States. The Forum provided the group of scholars with an opportunity for dedicated discussion and debate of the theme, stimulated by in-depth presentations and informal sharing of projects. A distinctive feature of SRTL's format is the emphasis on reflection and group discussion: a conference on student learning that is set up to foster deeper participant engagement and open-ended exploration than is usually available at lecture-oriented conferences.
Follow-up events are to include a book based on the scientific program, published through Catalyst Press, informal gatherings at other upcoming statistics education meetings, and ongoing research collaborations among many of the delegates. Plans are already underway for the next meeting (SRTL-9) in Germany in 2015.
The Forum was sponsored by The University of Minnesota, the Statistics Education Section of the American Statistical Association, Springer Publications, and Alakef Coffee Roasters.
Joan Garfield and Elizabeth Fry from The University of Minnesota led the local planning and organizing prior to the SRTL-8 gathering, supported by Bob delMas (University of Minnesota) and Dani Ben-Zvi (University of Haifa, Israel), who ensured that the forum ran smoothly. Thanks to the efforts of the local organizers, participants were able to not only enjoy each other’s creative efforts during the scientific program but also to appreciate the local culture and natural beauty of Minnesota’s north shore!

For further information please contact the SRTL co-chairs:
Joan Garfield,
Dani Ben-Zvi,

Scientific Program

George CobbStatistician's address: Reasoning about uncertainty: why our tensions are essential
Cliff KonoldUsing data and chance to make conclusions
Hana Manor Braham, Dani Ben-ZviStudents' reasoning about uncertainty while exploring sampling distributions in an "Integrated Approach"
Arthur Bakker, Dani Ben-Zvi, Katie MakarReducing uncertainty in a hospital laboratory: A vocational student's web of reasons and actions involved in making a statistical inference
Janet Ainley, Dani Ben-Zvi, Hana Manor Braham, Dave Pratt:Children's expressions of uncertainty in statistical modelling
Rob GouldTeaching data handling
Rolf Biehler, Daniel Frischemeier, Susanne PodwornyPreservice teachers' reasoning about uncertainty in the context of randomization tests
Luca ZapataPromoting the development of teachers' ideas of uncertainty
Sandra MaddenConstructing simulations and interrogating empirical sampling distributions supports teachers' reasoning in the presence of uncertainty
Pip Arnold, Stephanie Budgett, Maxine PfannkuchExperiment-to-causation inference: The emergence of new considerations regarding uncertainty
Robert delMas & Ethan BrownStudents' emerging reasoning with uncertainty in a randomization-based first course in statistics at the tertiary level
Jennifer NollFacilitating students' Reasoning about uncertainty in the context of making informal inferences: the role of curriculum and technology
Jill Fielding-Wells, Katie MakarInferring to a model: Using inquiry-based argumentation to challenge young children's expectations of equally likely outcomes
Sibel Kazak"How confident are you?" Supporting young students' reasoning about uncertainty in chance games through students' talk and computer simulations

Wednesday, September 4, 2013

Free Book—Statistical Thinking: A Simulation Approach to Modeling Uncertainty

(cross-posted from Citizen Statistician)

Catalyst Press has just released the second edition of the book Statistical Thinking: A Simulation Approach to Modeling Uncertainty. The material in the book is based on work related to the NSF-funded CATALST Project (DUE-0814433). It makes exclusive use of simulation to carry out inferential analyses. The material also builds on best practices and materials developed in statistics education, research and theory from cognitive science, as well as materials and methods that are successfully achieving parallel goals in other disciplines (e.g., mathematics and engineering education).

The materials in the book help students:
  • Build a foundation for statistical thinking through immersion in real world problems and data
  • Develop an appreciation for the use of data as evidence
  • Use simulation to address questions involving statistical inference including randomization tests and bootstrap intervals
  • Model and simulate data using TinkerPlots™ software
Why a cook on a statistics book? It is symbolic of a metaphor introduced by Alan Schoenfeld (1998) that posits many introductory (statistics) classes teach students how to follow “recipes”, but not how to really “cook.” That is, even if students leave a class able to perform routine procedures and tests, they do not have the big picture of the statistical process that will allow them to solve unfamiliar problems and to articulate and apply their understanding. Someone who knows how to cook knows the essential things to look for and focus on, and how to make adjustments on the fly. The materials in this book were intended to help teach students to “cook” (i.e., do statistics and think statistically).

The book is licensed under Creative Commons and is freely available on gitHub. If physical copies of the book are preferred, those are available for $45 at CreateSpace (or Amazon) in full color. All royalties from the book are donated to the Educational Psychology department at the University of Minnesota.