The first MOOC in statistics


Massive open online courses (MOOCs) are all the rage today. Some people see free online courses as a convenient way to introduce statistical concepts to tens of thousands of students who would not otherwise have an opportunity to learn about data analysis. Whereas 2013 is the International Year of Statistics, the New York Times christened 2012 the “year of the MOOC,” citing the more than one million students who took online courses (across all subjects) during 2012.

Impressive numbers. But what if I tell you that there was a statistics course that attracted 1.2 million students by itself? Furthermore, what if I tell you that the course was offered in 1960?

The story begins in 1957, when the Soviet Union successfully launched Sputnik I, the world's first artificial satellite. In response, the US government poured money into math and science education. Many of the nation’s top scientists developed new courses aimed to educate teachers and students in the fundamentals of math and science.

One of those scientists was Frederick Mosteller, a statistician at Harvard and a future president of the American Statistical Association, who wrote an elementary textbook on probability and statistics. His book was so popular that he was asked to be the lecturer for a nationally televised version of his course, to be shown on an NBC program known as Continental Classroom. The probability and statistics course was part of the third season of the show, which had featured physics and chemistry as topics for the first two seasons.

195 television stations broadcast the 30-minute show at 6:30 a.m. every weekday. More than 75,000 students took the course for credit through a nationwide arrangement with 320 colleges and universities. Exams were mailed to the colleges and administered by a local teacher who served as a course assistant. About 1.2 million people viewed the course for no credit by watching their local NBC affiliate station.

As is the case for today’s MOOCs, it is doubtful that all of the people who took the course mastered the material. However, the fact that 1.2 million people viewed the course is impressive. Today’s MOOCs have not managed to attract that many students, even though they have several advantages over Mosteller’s televised course. Today’s students can watch (and rewatch!) video lectures whenever it is convenient, rather than at 6:30 each morning. Furthermore, Internet technology provides today’s MOOCs with a global audience that can interact with each other and with teaching assistants 24/7.

Because the Internet had not been invented yet, it is a stretch to classify Mosteller’s course as “online.” However, it was definitely massive and open, so perhaps I should call it a MOC instead of a MOOC. Whatever you call it, Fred Mosteller’s Continental Classroom deserves to be remembered as a daring experiment that introduced many of the ideas for distance learning that are still being used 50 years later in the Internet Age.

For additional details on Continental Classroom see The Pleasure of Statistics: The Autobiography of Frederick Mosteller, from which most of the information in this article was taken (p. 259-264). The same book contains many more interesting stories about Mosteller, one of the preeminent statisticians of the 20th century.

Tags History

About Author

Rick Wicklin

Distinguished Researcher in Computational Statistics

Rick Wicklin, PhD, is a distinguished researcher in computational statistics at SAS and is a principal developer of PROC IML and SAS/IML Studio. His areas of expertise include computational statistics, simulation, statistical graphics, and modern methods in statistical data analysis. Rick is author of the books Statistical Programming with SAS/IML Software and Simulating Data with SAS.


    • Rick Wicklin

      Yes! The appendix of Mosteller's autobiography notes that in 2007, Judith Singer (one of Mosteller's last PhD students) tracked down 46 films from Continental Classroom. The ASA converted them to digital form and stored them in the ASA Archives Collection at Iowa State University. They can be viewed there. Unfortunately, the copyright is owned by the Ford Foundation (which sponsored the TV show), and so these videos are not available on the internet.

    • Rick Wicklin

      He also led one of the first research projects that used Bayesian analysis to solve a big (not a classroom exercise) research problem: Who wrote the disputed Federalist Papers, James Madison or Alexander Hamilton? The analysis of Mosteller and Wallace, which used frequency of words in the disputed articles, was a tour de force of (mostly hand) computations in the days before powerful computers were common. The conclusion was that Madison wrote all 12 of the disputed papers.

  1. Pingback: Links - Mind Your Decisions

  2. Pingback: 13 popular articles from 2013 - The DO Loop

Leave A Reply

Back to Top