Webinars

This webinar will describe an activity that uses data collected from an experiment looking at the relationship between two categorical variables: Whether a cotton plant was exposed to spider mites; and did the plant contract Wilt disease? The activity uses randomization to explore whether there is a difference between the occurrence of the disease with and without the mites. The webinar will include a discussion of the learning goals of the activity, followed by an implementation of the activity then suggestions for assessment. The implementation first uses a physical simulation, then a simulation using technology.

In Statistics as in many disciplines, students need to learn about complex concepts and dynamically changing processes. How can instructors help their students begin to "see" these complex topics the way experts do, and are there tools that can help? In this webinar, I will review key findings on how computer visualizations and simulations can best support student learning and then take those findings to generate effective strategies for teaching with simulations and visualizations.

A real-time online hands-on activity database is introduced for teaching introductory statistics. The activity, "How well can hand size predict height?", will be used to demonstrate how to use real-time activity to engage students to learn bivariate relationship. Various other activities can be found at stat.cst.cmich.edu/statact. The real-time database approach speeds up the process of data gathering and shifts the focus to engage students in the process of data production and statistical investigation.

Statistics educators are keenly aware of the value of using real data to help students see the relevance and applicability of statistics. The federal statistical agencies have invested in significant efforts to make data accessible and available. In this webinar, Ron Wasserstein will point you to these resources, discussing their uses and limitations.

An important idea in statistics is that the amount of data matters. We often teach this with formulas --- the standard error of the mean, the t-statistic, etc. --- in which the sample size appears in a denominator as √n. This is fine, so far as it goes, but it often fails to connect with a student's intuition. In this presentation, I'll describe a kinesthetic learning activity --- literally a random walk --- that helps drive home to students why more data is better and why the square-root arises naturally and can be understood by simple geometry. Students remember this activity and its lesson long after they have forgotten the formulas from their statistics class.

This webinar is based on the activity I found at www.lhs.logan.k12.ut.us/~jsmart/tank.htm and other on-line resources (see references). During World War II, the British and U.S. statisticians used estimation methods to deduce the productivity of Germany's armament factories using serial numbers found on captured equipment, such as tanks. The tanks were numbered in a manner similar to 1, 2, 3, ..., N, and the goal of the allies was to estimate the population maximum N from their collected sample of serial numbers. The purpose of this activity is to introduce students to the concept of an unbiased estimator of a population parameter. Students will develop several estimators for the parameter N and compare them by running simulations in Minitab.

Many introductory Statistics courses consist of two main components: lecture sections and computer laboratory sections. In the computer labs, students often review fundamental course concepts, learn to analyze data using statistical software, and practice applying their knowledge to real world scenarios. Lab time could be better utilized if students arrived with 1) prior exposure to the core statistical ideas, and 2) a basic familiarity with the statistical software package. To achieve these objectives, PreLabs have been integrated into an introductory statistics course. A simple screen capture software (Jing) was used to create videos. The videos and a very short corresponding assignment together form a PreLab and are made available to students to access at appropriate times in the course. Some PreLabs were created to expose the students to statistical software details. Other PreLabs incorporate an available online learning resource or applet which allows students to gain a deeper understanding of a course concept through simulation and visualization. Not all on-line learning resources are ready to use 'as in' in a course. Some may be lacking a preface or description on how they are to be used; others may use slightly different notation or language than your students are accustomed to; a few may even contain an error or item that needs some clarification. One solution to such difficulties was to create a video wrapper so students can see how the applet works while receiving guidance from the instructor. In this webinar we will share the success story of how one introductory Statistics course integrated these video wrappers into the course and the discuss other possible applications.

In a classroom setting, students can engage in hands-on activities in order to better understand certain concepts and ideas. Replicating hands-on activities in an online environment, however, can be a challenge for instructors. The purpose of this webinar is to present an applet that was created to replicate a "Post-it Note" activity we commonly use in classroom sections of an undergraduate introductory statistics course. The Post-it Note activity is meant to help students develop a more conceptual understanding of the mean and the median by moving a set of Post-it Notes along a number line. During the webinar, participants will have an opportunity to see and experience just how online students are able to interact with what we have named the "Sticky Centers" applet, and we will present the kinds of materials and assignments we have created to use in conjunction with this applet. The webinar will end with a preview a newer applet we are working on in order to replicate the famous "Gummy Bears in Space" activity (presented in Schaeffer, Gnanadesikan, Watkins & Witmer, 1996).

Many of us, while teaching an introductory statistics course, have mentioned some of the history behind the methodology, perhaps just in passing. We might remark that an English chap by the name of R. A. Fisher is responsible for a great deal of the course content. We could further point out that the statistical techniques used in research today were developed within the last century, for the most part. At most, we might reveal the identity of the mysterious "Student" when introducing the t-test to our class. I propose that we do more of this. This webinar will highlight some opportunities to give brief history lessons while teaching an introductory statistics course.

Based on an activity by John Spurrier, we use a baseball example to introduce students to Bayesian estimation. Students use prior information to determine prior distributions which lead to different estimators of the probability of a hit in baseball. We also compare our different Bayesian estimators and different frequentist estimators using bias, variability, and mean squared error. We can see the effect that sample size and dispersion of the prior distribution have on the estimator.