Roosevelt University Economist Who Challenged Use of Statistics Celebrates Victory

Steve Ziliak

CHICAGO–(ENEWSPF)–March 17, 2016.  After more than two decades of challenging the way scientists use statistics, Roosevelt University Economics Professor Stephen T. Ziliak is celebrating a victory that could bring a sea change to the way research is done and standards are used to justify findings.

Lead author of the critically-acclaimed book, The Cult of Statistical Significance: How the Standard Error Costs Us Jobs, Justice and Lives (2008), Ziliak envisions a paradigm shift for scientific research and reasoning now that the American Statistical Association (ASA) has formally come out against flawed statistical testing methods that the professor has been challenging since 1988.

“It is a liberating moment for scientific researchers using statistics in fields from agronomy to zoology,” said Ziliak of the ASA’s groundbreaking March 7, 2016, statement that takes issue with statistical significance testing, especially the test known as the p-value.

Ziliak was a lead writer on the expert team that drafted the revolutionary new statement at

In the statement, the ASA takes issue with the long-embraced notion that statistical significance, such as “p < 0.05,” correctly measures the probability of a researcher’s hypothesis being true. It also challenges the idea and common practice of basing scientific conclusions, business and policy decisions on statistical significance testing.

“The scientific community no longer will be required to use methods that have been shown repeatedly to arrive at mistaken conclusions,” said Ziliak, who was the only economist on the 26-member team of experts that met at ASA headquarters in October 2015 to weigh in on a framework for the new ASA policy.

“This is big.  It has the potential to completely change the nature of our scientific inquiry – from how we do our research, to the way grants are awarded as well as the standards we are using to gain approval for new products and results, including medicine and drugs,” he said.

Ziliak first began questioning the use of statistical significance in 1988 in his job as economist for the Indiana Department of Workforce Development. Ziliak was not allowed to publish data on, nor to discuss, black youth unemployment rates on grounds that the p-values were too high.  “I was baffled, and decided then and there to do something about it.”

As a University of Iowa PhD student in Economics, he argued that statistical significance testing – long the gold standard for scientific research – was seriously flawed in a well-known 1996 journal article entitled “The Standard Error of Regressions.” Today, he has more than 30 journal articles and essays on the topic, including a U.S. Supreme Court brief and the book The Cult of Statistical Significance.

“When I came out of graduate school, I was told by my professors not to mention the topic, that it was too controversial, and that I wouldn’t be able to get a job if I opposed statistical significance testing,” he said. “Several professors told me to remove the 1996 article from my CV.  With this new ASA statement, I’ve gone from radical to mainstream,” added Ziliak, who helped craft the statement with experts from a variety of fields including medicine, epidemiology, psychology, political science, environmental science, philosophy and nuclear engineering.

“Together we agreed that the current culture of statistical significance testing, interpretation and reporting has to go, and that adherence to a minimum of six principles can help to pave the way forward for science and society,” Ziliak writes in a new article entitled “The Significance of the ASA Statement on Statistical Significance and P-Values” that is in the March issue of The American Statistician.

“There is a hunger for change among journal editors and referees; among grantors and journalists, lawyers and decision makers,” writes Ziliak, who has long argued that economic significance—the magnitude of effect sizes and the consequences of being incorrect in judgment—matter more than statistical significance.

For more information, contact Ziliak at [email protected] or 312-341-3763.  To learn more about his pioneering research visit his website at