I have heard a number of stories about how mint and year affect the percentage of heads for spun pennies. Does anyone have any hard data on this? I have not spun pennies in some years, but when I did I gathered enough data to make me question the stories I had heard.
One thing I learned from coin activities is that modern youth -- especially modern male youth -- don't carry any coins with them. So, I provided coins haphazardly chosen from the accumulation on my nightstand. I then collected the coins and the results from each student. There was a LOT more variability than I would expect if p=0.50 for all pennies. So, I packaged the pennies in numbered envelopes and tried them with one or two other classes. Generally, they replicated the results of the first. Pennies that gave unusually large numbers of heads with one class did so with another. (One class never knew the results of previous classes until AFTER they spun the pennies and reported THEIR results.) However, another penny of the same date and mint might give consistent results around p=0.5 or even p<0.5. So, I wondered if the things I had heard were based on large numbers of pennies matched for year and mint, or if someone just happened to have a 1953 penny that acted weird but was simply ASSUMING that to be a property of all 1953 pennies rather than that individual.
This seems like an activity of interest to high school teachers and students, who may have more time for activities, so perhaps people would like to pool their results into a National Investigation of Spun Penny Orientation (NISPO). (I only had students spin pennies in classes that met in a room with flat desks -- an unusual event around here.)
_ | | Robert W. Hayden | | Department of Mathematics / | Plymouth State College MSC#29 | | Plymouth, New Hampshire 03264 USA | * | Rural Route 1, Box 10 / | Ashland, NH 03217-9702 | ) (603) 968-9914 (home) L_____/ firstname.lastname@example.org fax (603) 535-2943 (work)