Content area
Full text
IN 1951, WHEN PAUL MEIER received his doctorate in mathematics from Princeton University and became one of the first statisticians to enter medical research, potential new medical treatments were evaluated in a very different fashion than they are today. At the time, researchers commonly followed practices such as giving a new remedy to patients they thought might benefit from it and comparing the outcomes with other patients who were not treated. In other situations, patients who stopped taking a new medicine might be counted as controls who had never been exposed to it.
Meier, who died on August 7, 2011, at the age of 87, had a profound impact on how clinical trials now evaluate the efficacy of new drugs and treatment methodologies throughout the world. Meier's "many published works and writings have had a huge influence on the application of statistics to medical research- particularly the design, conduct, and analysis of randomized clinical trials and in the advancement of evidence-based medicine in general," according to the Society of Clinical Trials, which Meier helped found in 1978.1
Meier was tireless in his promotion of the now-standard practice of randomly assigning patients enrolled in clinical trials to receive either the conventional remedy or the new treatment being evaluated. This is now considered the most rigorous way to conduct a study and the best way to gather evidence of a new drug or treatment's effectiveness. "Perhaps more than any other U.S. statistician, [Dr. Meier] influenced U.S. drug regulatory agencies, and hence clinical researchers throughout the U.S. and other countries, to insist on the central importance of randomized evidence," said Sir Richard Peto of Oxford University, who was also a leading advocate for randomization, in Meier's New York Times obituary.2 "That strategic decision half a century ago has already saved millions of lives, and those millions should be attributed to Paul," Peto said.
"I defended randomization every chance I got, and I had a fair number of chances," Meier said in a 2003 interview in the journal Clinical Trials.3(p137) "For a fairly long time randomization was not thought of so highly," he explained. He said that in 2001,
a very distinguished statistician told me that I had a major influence on the Food and Drug Administration's policies on...