A cartoon to aid in discussing confounding and correlative versus causal relationships, for example by asking students to suggest an alternate reason for the relationship besides the one jokingly illustrated in the cartoon. The cartoon was created by English cartoonist John Landers in December, 2021 based on an idea by Dennis Pearl (Penn State University) and Larry Lesser (The University of Texas at El Paso).
A video using dance to teach about concepts involved with correlation. This 2013 video is from the “Dancing Statistics” series developed by Lucy Irving from Middlesex University (UK) funded by a BPS Public Engagement grant and additional funding from IdeasTap. Full credits are within the video. The Dancing Statistics project is described at https://www.frontiersin.org/articles/10.3389/fpsyg.2015.00050/full
The video also comes with teaching notes for viewing by instructors who are logged into CAUSEweb.org.
A 2020 cartoon illustrating the idea of heteroscedasticity (non-constant variance) that might be used to start a discussion on the important of the constant variance of errors in making inferences from regression models. The cartoon was used in a 2021 Teaching Statistics paper "Statistical edutainment that lines up and fits," by Dennis Pearl from Penn State University and Larry Lesser from The University of Texas at El Paso.
A quick "hands on" activity for an in-class experience of data collection as a simple linear regression example where students predict the time needed for a human chain of hand squeezes to make a full circuit as a function of number of people in the chain. The lesson plan secondary school lesson plan adapted from Cynthia Lanius’ hand squeeze activity by Bo Brawner at Tarleton State University.
A cartoon designed to support a discussion of using dummy variables to code for categories of a categorical variable in a regression model (e.g. 5 are needed when there are 6 categories). The cartoon was used in the February 2020 CAUSE cartoon caption contest and the winning caption was written by Dominic Matriccino, a student at the University of Virginia. The cartoon was drawn by British cartoonist John Landers (www.landers.co.uk) based on an idea by Dennis Pearl from Penn State University. A second winner in the February 2020 contest was "The grass really is greener on the homogeneity side," written by Jennifer Ann Morrow, an instructor from University of Tennessee. Jennifer's cartoon caption can be used in discussing the importance of within-group variability in judging differences between groups and the difficulty when the groups being compared have different levels of variability.
A cartoon that can be used for discussing the traditional theme of "Correlation does not imply Causation" as well as what observational evidence does provide the most convincing evidence of a causal relationship. The cartoon was used in the June 2019 CAUSE cartoon caption contest. The cartoon was drawn by British cartoonist John Landers (www.landers.co.uk) based on an idea by Dennis Pearl from Penn State University.
A cartoon to initiate discussions about how the correlation is a unitless number that does not change with changes in the units of the variables involved. The cartoon was created in February 2020 by British caetoonist John Landers based on an idea by Dennis Pearl (Penn State) and Larry Lesser (Univ of Texas at El Paso). An outline of a lesson plan for the use of the cartoon is given in a 2020 Teaching Statistics article by Dennis Pearl and Larry Lesser.
A poem written in 2019 by Larry Lesser from The University of Texas at El Paso to discuss the simplest case of line of fit where the slope and correlation coefficients each have a value of 0. The poem is part of a collection of 8 poems published with commentary in the January 2020 issue of Journal of Humanistic Mathematics.
A joke to use in discussing the meaning of the slope in a linear trend. The joke was written in May 2019 by Larry Lesser, The University of Texas at El Paso, and Dennis Pearl, Penn State University.
This paper comes from researchers at the NASA Langley Research Center and College of William & Mary.
"The experience of retinex image processing has prompted us to reconsider fundamental aspects of imaging and image processing. Foremost is the idea that a good visual representation requires a non-linear transformation of the recorded (approximately linear) image data. Further, this transformation appears to converge on a specific distribution. Here we investigate the connection between numerical and visual phenomena. Specifically the questions explored are: (1) Is there a well-defined consistent statistical character associated with good visual representations? (2) Does there exist an ideal visual image? And (3) what are its statistical properties?"