Demonstrating the Gambler's Fallacy in an introductory statistics class

In this article, we describe a classroom demonstration that uses the Gamble r's Fallacy to illustrate misconceptions about random processes and how the y affect statistical interpretation. The demonstration used a database coll ected from simulated gambling by students picking professional football gam es with the point spread (i.e., a real-life random process). The results of student picks illustrated chat random processes are not self-correcting an d reinforced the relation between sample size and variability. Formal and i nformal feedback from students indicated that the demonstration was well re ceived and recommended for future classes.