Dennis Pearl, The Ohio State University
Tuesday, May 26, 2009 - 2:30pm ET
This webinar will describe a computer lab activity using the Flash-based applet at www.causeweb.org/mouse_experiment to teach key principles regarding the value of random assignment:
how it helps to eliminate bias when compared with a haphazard assignment process,
how it leads to a consistent pattern of results when repeated, and
how it makes the question of statistical significance interesting since differences between groups are either from treatment or by the luck of the draw.
In this webinar, the activity will be demonstrated along with a discussion of goals, context, background materials, class handouts, and assessments.
Laura Kubatko, The Ohio State University; Danny Kaplan, Macalester College; and Jeff Knisley, East Tennessee State University
Tuesday, May 12, 2009 - 2:00pm ET
National reports such as Bio2010 have called for drastic improvements in the quantitative education that biology students receive. The three panelists are involved in three differently structured integrative programs aimed to give biology students the statistics that are useful in learning and doing biology.
The three programs have some surprising things in common for teaching introductory statistics. All three involve connecting calculus and statistics. All three reach beyond the mathematical topics usually encountered in intro statistics in important ways. All three aim to keep the mathematics and statistics strongly connected to biology.
The panelists will describe their different approaches to teaching statistics for biology and discuss how and why an integrated approach gives advantages. Important issues are how to tie statistics advantageously with calculus, how to keep "advanced" mathematical and statistical topics accessible to introductory-level biology students, and how to employ computation productively. The discussion will contrast a comprehensive "team" approach (at ETSU) with stand-alone courses (at Macalester and at OSU) and will refer to the institutional opportunities and constraints that have shaped the programs at their different institutions.
Herbert Lee, University of California - Santa Cruz
Tuesday, April 28, 2009 - 2:30pm ET
Getting and retaining the attention of students in an introductory statistics course can be a challenge, and poor motivation or outright fear of mathematical concepts can hinder learning. By using an example as familiar and comforting as chocolate chip cookies, the instructor can make a variety of statistical concepts come to life for the students, greatly enhancing learning. Topics from variability and exploratory data analysis to hypothesis testing and Bayesian statistics can be illuminated with cookies.
Allan Rossman & Beth Chance, Cal Poly - San Luis Obispo; and John Holcomb, Cleveland State University
Tuesday, April 14, 2009 - 2:00pm ET
We present ideas and activities for helping students to learn fundamental concepts of statistical inference with a randomization-based curriculum rather than normal-based inference. We propose that this approach leads to deeper conceptual understanding, makes a clear connection between study design and scope of conclusions, and provides a powerful and generalizable analysis framework. During this webinar we present arguments in favor of such a curriculum, demonstrate some activities through which students can investigate these concepts, highlight some difficulties with implementing this approach, and discuss ideas for assessing student understanding of inference concepts and randomization procedures.
Watch Webinar Recording (FLASH)
Nicholas Horton, Smith College
Tuesday, March 24, 2009 - 2:30pm ET
Students have a hard time making the connection between variance and risk. To convey the connection, Foster and Stine (Being Warren Buffett: A Classroom Simulation of Risk and Wealth when Investing in the Stock Market (see materials) The American Statistician, 2006, 60:53-60) developed a classroom simulation. In the simulation, groups of students roll three colored dice that determine the success of three "investments". The simulated investments behave quite differently. The value of one remains almost constant, another drifts slowly upward, and the third climbs to extremes or plummets. As the simulation proceeds, some groups have great success with this last investment--they become the "Warren Buffetts" of the class. For most groups, however, this last investment leads to ruin because of variance in its returns. The marked difference in outcomes shows students how hard it is to separate luck from skill. The simulation also demonstrates how portfolios, weighted combinations of investments, reduce the variance. In the simulation, a mixture of two poor investments is surprisingly good.
In this webinar, the activity will be demonstrated along with a discussion of goals, context, background materials, class handouts, and references.
Jennifer Kaplan, Michigan State University
Tuesday, March 10, 2009 - 2:00pm ET
Central to the recommendations for teaching introductory statistics made by the GAISE committee were the following: foster active learning in the classroom, use assessment to improve and evaluate student learning, and use real data (GAISE, 2006). This session will illustrate how personal response systems (clickers) can be used to address the realization of these three recommendations in large lecture classes (over 70 students). The session will discuss general issues of the implementation of clickers and then provide an example of each of the following three uses of clickers in the classroom: 1) questions designed to highlight common conceptual misunderstandings in statistics, 2) questions designed as review questions for topics already addressed, and 3) questions that were part of a class activity to help students learn a concept.
Watch Webinar Recording (FLASH)
Andrew Zieffler, Bob delMas, and Joan Garfield, University of Minnesota
Tuesday, February 10, 2009 - 2:00pm ET
This webinar presents an overview of the materials and research-based pedagogical approach to helping students reason about important statistical concepts. The materials presented were developed by the NSF-funded AIMS (adapting and Implementing Innovative Materials in Statistics) project at the University of Minnesota (www.tc.umn.edu/~aims).
Watch Webinar Recording (FLASH)
Jo Hardin, Pomona College
Tuesday, January 13, 2009 - 2:00pm ET
This webinar will discuss the development and teaching of a freshman seminar course. In this course, students investigate the practical, ethical, and philosophical issues raised by the use of statistics and probabilistic thinking in realms such as politics, medicine, sports, the law, and genetics. Students explore issues from fiction, the mainstream media, and scientific articles in peer-reviewed journals. To do all of this, they must consider a wide range of statistical topics as well as encountering a range of uses and abuses of statistics in the world today.
Watch Webinar Recording (FLASH)
John H. Walker, California Polytechnic State University
Tuesday, December 9, 2008 - 2:00pm ET
Ethics play an important role in statistical practice. How can we educate our students about statistical ethics--especially when our courses are already packed with so much...statistics? At the Joint Statistical Meetings in August, I was the discussant in a session on "Teaching Ethics in Statistics Class." First, I will briefly review the points raised by the speakers in that session. George McCabe (Purdue) contrasted the "old" introductory statistics course with its emphasis on methodology to the "new" course. Patricia Humphrey (Georgia Southern) spoke about how she covers ethical data collection in her introductory classes. Paul Velleman (Cornell) talked about the role of judgment in statistical model building and how it makes students (and sometimes us) uncomfortable. I will discuss each of these points in the context of the American Statistical Association's "Ethical Guidelines for Statistical Practice" as well as my own experiences in teaching statistical ethics in an undergraduate capstone course for statistics majors. I will close with an example of statistical ethics in the use of multiple comparison procedures.
Watch Webinar Recording (FLASH)
Xiao-Li Meng, with Happy Team members: Yves Chretien, Paul Edlefsen, Kari Lock, and Cassandra Wolos; Department of Statistics, Harvard University
Tuesday, November 18, 2008 - 2:00pm ET
Statistics 105 is a team-designed course that has received local media attention (e.g., www.news.harvard.edu/gazette/2008/02.14/11-stats.html). Its course description promises the following:
Discover an appreciation of statistical principles and reasoning via "Real-Life Modules" that can make you rich or poor (financial investments), loved or lonely (on-line dating), healthy or ill (clinical trials), satisfied or frustrated (chocolate/wine tasting) and more. Guaranteed to bring happiness (or misery) both to students who have never taken a previous statistics course, and to those who have taken statistics and want to see how statistical thinking applies to so many areas of life.
This webinar will reveal its history, pedagogical motivation, innovations, and challenges along the way.
Watch Webinar Recording (FLASH)