The Little-Known Statistician Who Taught Us to Measure Teachers

He was raised on a small dairy farm and earned a doctorate in statistics and quantitative genetics from the University of Tennessee. At the time, Oak Ridge National Laboratory, near Knoxville, was studying the effects of radiation on living things.

Nuclear weapons tests had released clouds of radiation that had drifted with the weather. Sometime later, farm animals downwind began to die. Did the first event, a mushroom cloud, cause the second event, dead sheep? Or did one merely follow the other coincidentally? Solving this problem required expertise in both statistical probability and livestock biology. Oak Ridge hired Bill Sanders.

Then, in 1982, Mr. Sanders chanced upon a newspaper article about the latest controversy in K-12 education.

Photo

William S. Sanders, who sought to measure the “value-added” contributions of individual teachers.

Credit
Courtesy of SAS

Tennessee’s governor, Lamar Alexander, who is now chairman of the Senate education committee, wanted to give more status and money to the best schoolteachers. That raised a thorny question: What, exactly, does “best” mean?

Mr. Sanders and a colleague sent Mr. Alexander a letter offering to help. Mr. Alexander ultimately chose not to use Mr. Sanders’s method, but eight years later, Mr. Sanders was summoned by Gov. Ned McWherter to make his case.

Tennessee, an early adopter in standardized testing, administered annual exams in five subjects. Those scores, Mr. Sanders said, could gauge the quality of the students’ teachers. Yet, he cautioned, a simple comparison of a student’s test scores with her scores a year before wasn’t good enough.

Imagine two students. Both start the year at the same level in math, and both improve by 15 percent. But in previous years, the first student…

Read the full article from the Source…

Back to Top